{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:23:07Z","timestamp":1780053787902,"version":"3.54.0"},"reference-count":324,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s10462-020-09888-5","type":"journal-article","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T07:02:30Z","timestamp":1597647750000},"page":"1677-1734","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":446,"title":["Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review"],"prefix":"10.1007","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7534-2396","authenticated-orcid":false,"given":"Guoguang","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,8,17]]},"reference":[{"key":"9888_CR1","unstructured":"Akkaya I, Andrychowicz M, Chociej M, Litwin M, McGrew B, Petron A, Paino A, Plappert M, Powell G, Ribas R, et\u00a0al (2019) Solving rubik\u2019s cube with a robot hand. Preprint arXiv:1910.07113"},{"key":"9888_CR2","doi-asserted-by":"crossref","unstructured":"Aldoma A, Vincze M, Blodow N, Gossow D, Gedikli S, Rusu RB, Bradski G (2011) Cad-model recognition and 6dof pose estimation using 3d cues. In: 2011 IEEE international conference on computer vision workshops (ICCV workshops), IEEE, pp 585\u2013592","DOI":"10.1109\/ICCVW.2011.6130296"},{"key":"9888_CR3","doi-asserted-by":"crossref","unstructured":"Aoki Y, Goforth H, Srivatsan RA, Lucey S (2019) Pointnetlk: robust & efficient point cloud registration using pointnet. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7163\u20137172","DOI":"10.1109\/CVPR.2019.00733"},{"issue":"4","key":"9888_CR4","doi-asserted-by":"crossref","first-page":"4571","DOI":"10.1109\/LRA.2019.2933815","volume":"4","author":"P Ard\u00f3n","year":"2019","unstructured":"Ard\u00f3n P, Pairet \u00c8, Petrick RP, Ramamoorthy S, Lohan KS (2019) Learning grasp affordance reasoning through semantic relations. IEEE Robot Autom Lett 4(4):4571\u20134578","journal-title":"IEEE Robot Autom Lett"},{"key":"9888_CR5","doi-asserted-by":"crossref","unstructured":"Asif U, Tang J, Harrer S (2018) Graspnet: an efficient convolutional neural network for real-time grasp detection for low-powered devices. In: IJCAI, pp 4875\u20134882","DOI":"10.24963\/ijcai.2018\/677"},{"key":"9888_CR6","doi-asserted-by":"crossref","unstructured":"Bay H, Tuytelaars T, Van\u00a0Gool L (2006) Surf: speeded up robust features. In: European conference on computer vision, Springer, pp 404\u2013417","DOI":"10.1007\/11744023_32"},{"key":"9888_CR7","unstructured":"Bellekens B, Spruyt V, Berkvens R, Weyn M (2014) A survey of rigid 3d pointcloud registration algorithms. In: AMBIENT 2014: the fourth international conference on ambient computing, applications, services and technologies, August 24\u201328, 2014, Rome, Italy, pp 8\u201313"},{"issue":"4","key":"9888_CR8","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/34.993558","volume":"24","author":"S Belongie","year":"2002","unstructured":"Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509\u2013522","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR9","doi-asserted-by":"crossref","unstructured":"Berscheid L, Mei\u00dfner P, Kr\u00f6ger T (2019) Robot learning of shifting objects for grasping in cluttered environments. Preprint arXiv:1907.11035","DOI":"10.1109\/IROS40897.2019.8968042"},{"issue":"2","key":"9888_CR10","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/34.121791","volume":"14","author":"PJ Besl","year":"1992","unstructured":"Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239\u2013256","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"03","key":"9888_CR11","first-page":"102","volume":"4","author":"S Bhatia","year":"2013","unstructured":"Bhatia S, Chalup SK et al (2013) Segmenting salient objects in 3d point clouds of indoor scenes using geodesic distances. J Signal Inf Process 4(03):102","journal-title":"J Signal Inf Process"},{"key":"9888_CR12","unstructured":"Billings G, Johnson-Roberson M (2018) Silhonet: An RGB method for 3d object pose estimation and grasp planning. CoRR abs\/1809.06893"},{"key":"9888_CR13","unstructured":"Blomqvist K, Breyer M, Cramariuc A, F\u00f6rster J, Grinvald M, Tschopp F, Chung JJ, Ott L, Nieto J, Siegwart R (2020) Go fetch: mobile manipulation in unstructured environments. Preprint arXiv:2004.00899"},{"key":"9888_CR14","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. Preprint arXiv:2004.10934"},{"issue":"4","key":"9888_CR15","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.robot.2009.10.003","volume":"58","author":"J Bohg","year":"2010","unstructured":"Bohg J, Kragic D (2010) Learning grasping points with shape context. Robot Auton Syst 58(4):362\u2013377","journal-title":"Robot Auton Syst"},{"issue":"2","key":"9888_CR16","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","volume":"30","author":"J Bohg","year":"2014","unstructured":"Bohg J, Morales A, Asfour T, Kragic D (2014) Data-driven grasp synthesis: a survey. IEEE Trans Robot 30(2):289\u2013309","journal-title":"IEEE Trans Robot"},{"key":"9888_CR17","doi-asserted-by":"crossref","unstructured":"Bolya D, Zhou C, Xiao F, Lee YJ (2019) Yolact++: better real-time instance segmentation. Preprint arXiv:1912.06218","DOI":"10.1109\/ICCV.2019.00925"},{"key":"9888_CR18","doi-asserted-by":"crossref","unstructured":"Bolya D, Zhou C, Xiao F, Lee YJ (2019) Yolact: real-time instance segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 9157\u20139166","DOI":"10.1109\/ICCV.2019.00925"},{"issue":"2","key":"9888_CR19","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji A, Cheng MM, Hou Q, Jiang H, Li J (2019) Salient object detection: A survey. Computational visual media 5(2):117\u2013150","journal-title":"Computational visual media"},{"key":"9888_CR20","doi-asserted-by":"crossref","unstructured":"Borst C, Fischer M, Hirzinger G (2003) Grasping the dice by dicing the grasp. In: IEEE\/RSJ international conference on intelligent robots and systems, IEEE, vol\u00a04, pp 3692\u20133697","DOI":"10.1109\/IROS.2003.1249729"},{"key":"9888_CR21","doi-asserted-by":"crossref","unstructured":"Bousmalis K, Irpan A, Wohlhart P, Bai Y, Kelcey M, Kalakrishnan M, Downs L, Ibarz J, Pastor P, Konolige K et\u00a0al (2018) Using simulation and domain adaptation to improve efficiency of deep robotic grasping. In: 2018 IEEE international conference on robotics and automation (ICRA), IEEE, pp 4243\u20134250","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"9888_CR22","doi-asserted-by":"crossref","unstructured":"Brachmann E, Krull A, Michel F, Gumhold S, Shotton J, Rother C (2014) Learning 6d object pose estimation using 3d object coordinates. In: European conference on computer vision, Springer, pp 536\u2013551","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"9888_CR23","doi-asserted-by":"crossref","unstructured":"Brachmann E, Michel F, Krull A, Ying\u00a0Yang M, Gumhold S et\u00a0al (2016) Uncertainty-driven 6d pose estimation of objects and scenes from a single rgb image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3364\u20133372","DOI":"10.1109\/CVPR.2016.366"},{"key":"9888_CR24","unstructured":"Bradski G, Kaehler A (2008) Learning OpenCV: computer vision with the OpenCV library. \u201c O\u2019Reilly Media, Inc.\u201d"},{"key":"9888_CR25","doi-asserted-by":"crossref","unstructured":"Cai J, Cheng H, Zhang Z, Su J (2019) Metagrasp: data efficient grasping by affordance interpreter network. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 4960\u20134966","DOI":"10.1109\/ICRA.2019.8793912"},{"issue":"3","key":"9888_CR26","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3390\/mti2030057","volume":"2","author":"S Caldera","year":"2018","unstructured":"Caldera S, Rassau A, Chai D (2018) Review of deep learning methods in robotic grasp detection. Multimodal Technol Interact 2(3):57","journal-title":"Multimodal Technol Interact"},{"key":"9888_CR27","doi-asserted-by":"crossref","unstructured":"Castro P, Armagan A, Kim TK (2020) Accurate 6d object pose estimation by pose conditioned mesh reconstruction. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 4147\u20134151","DOI":"10.1109\/ICASSP40776.2020.9053627"},{"key":"9888_CR28","doi-asserted-by":"crossref","unstructured":"Chen D, Li J, Wang Z, Xu K (2020) Learning canonical shape space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11973\u201311982","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"9888_CR29","doi-asserted-by":"crossref","unstructured":"Chen H, Li Y (2018) Progressively complementarity-aware fusion network for rgb-d salient object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3051\u20133060","DOI":"10.1109\/CVPR.2018.00322"},{"key":"9888_CR30","unstructured":"Chen H, Li Y (2019) Cnn-based rgb-d salient object detection: learn, select and fuse. Preprint arXiv:1909.09309"},{"key":"9888_CR31","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1016\/j.patcog.2018.08.007","volume":"86","author":"H Chen","year":"2019","unstructured":"Chen H, Li Y, Su D (2019) Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for rgb-d salient object detection. Pattern Recogn 86:376\u2013385","journal-title":"Pattern Recogn"},{"key":"9888_CR32","doi-asserted-by":"crossref","unstructured":"Chen H, Sun K, Tian Z, Shen C, Huang Y, Yan Y (2020) Blendmask: top-down meets bottom-up for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8573\u20138581","DOI":"10.1109\/CVPR42600.2020.00860"},{"issue":"4","key":"9888_CR33","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/70.246063","volume":"9","author":"IM Chen","year":"1993","unstructured":"Chen IM, Burdick JW (1993) Finding antipodal point grasps on irregularly shaped objects. IEEE Trans Robot Autom 9(4):507\u2013512","journal-title":"IEEE Trans Robot Autom"},{"key":"9888_CR34","doi-asserted-by":"crossref","unstructured":"Chen K, Pang J, Wang J, Xiong Y, Li X, Sun S, Feng W, Liu Z, Shi J, Ouyang W, et\u00a0al (2019) Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4974\u20134983","DOI":"10.1109\/CVPR.2019.00511"},{"key":"9888_CR35","doi-asserted-by":"crossref","unstructured":"Chen LC, Hermans A, Papandreou G, Schroff F, Wang P, Adam H (2018) Masklab: instance segmentation by refining object detection with semantic and direction features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4013\u20134022","DOI":"10.1109\/CVPR.2018.00422"},{"key":"9888_CR36","doi-asserted-by":"crossref","unstructured":"Chen W, Jia X, Chang HJ, Duan J, Leonardis A (2020) G2l-net: global to local network for real-time 6d pose estimation with embedding vector features. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4233\u20134242","DOI":"10.1109\/CVPR42600.2020.00429"},{"key":"9888_CR37","doi-asserted-by":"crossref","unstructured":"Chen X, Girshick R, He K, Doll\u00e1r P (2019) Tensormask: a foundation for dense object segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 2061\u20132069","DOI":"10.1109\/ICCV.2019.00215"},{"key":"9888_CR38","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1907\u20131915","DOI":"10.1109\/CVPR.2017.691"},{"issue":"3","key":"9888_CR39","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2014","unstructured":"Cheng MM, Mitra NJ, Huang X, Torr PH, Hu SM (2014) Global contrast based salient region detection. IEEE Trans Pattern Anal Mach Intell 37(3):569\u2013582","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR40","doi-asserted-by":"crossref","unstructured":"Choy C, Dong W, Koltun V (2020) Deep global registration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2514\u20132523","DOI":"10.1109\/CVPR42600.2020.00259"},{"issue":"4","key":"9888_CR41","doi-asserted-by":"crossref","first-page":"3355","DOI":"10.1109\/LRA.2018.2852777","volume":"3","author":"FJ Chu","year":"2018","unstructured":"Chu FJ, Xu R, Vela PA (2018) Real-world multiobject, multigrasp detection. IEEE Robot Autom Lett 3(4):3355\u20133362","journal-title":"IEEE Robot Autom Lett"},{"key":"9888_CR42","unstructured":"Chu FJ, Xu R, Vela PA (2019) Detecting robotic affordances on novel objects with regional attention and attributes. Preprint arXiv:1909.05770"},{"issue":"6","key":"9888_CR43","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1109\/TPAMI.2017.2708711","volume":"40","author":"A Crivellaro","year":"2017","unstructured":"Crivellaro A, Rad M, Verdie Y, Yi KM, Fua P, Lepetit V (2017) Robust 3d object tracking from monocular images using stable parts. IEEE Trans Pattern Anal Mach Intell 40(6):1465\u20131479","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"9888_CR44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3054739","volume":"36","author":"A Dai","year":"2017","unstructured":"Dai A, Nie\u00dfner M, Zollh\u00f6fer M, Izadi S, Theobalt C (2017) Bundlefusion: real-time globally consistent 3d reconstruction using on-the-fly surface reintegration. ACM Trans Graph (ToG) 36(4):1","journal-title":"ACM Trans Graph (ToG)"},{"key":"9888_CR45","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Li Y, Ren S, Sun J (2016) Instance-sensitive fully convolutional networks. In: European conference on computer vision, Springer, pp 534\u2013549","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"9888_CR46","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2016) Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3150\u20133158","DOI":"10.1109\/CVPR.2016.343"},{"key":"9888_CR47","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: object detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379\u2013387"},{"key":"9888_CR48","doi-asserted-by":"crossref","unstructured":"Danielczuk M, Matl M, Gupta S, Li A, Lee A, Mahler J, Goldberg K (2019) Segmenting unknown 3d objects from real depth images using mask r-cnn trained on synthetic data. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 7283\u20137290","DOI":"10.1109\/ICRA.2019.8793744"},{"key":"9888_CR49","doi-asserted-by":"crossref","unstructured":"Deng X, Xiang Y, Mousavian A, Eppner C, Bretl T, Fox D (2020) Self-supervised 6d object pose estimation for robot manipulation. In: International conference on robotics and automation (ICRA)","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"9888_CR50","doi-asserted-by":"crossref","unstructured":"Depierre A, Dellandr\u00e9a E, Chen L (2018) Jacquard: a large scale dataset for robotic grasp detection. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 3511\u20133516","DOI":"10.1109\/IROS.2018.8593950"},{"key":"9888_CR51","unstructured":"Depierre A, Dellandr\u00e9a E, Chen L (2020) Optimizing correlated graspability score and grasp regression for better grasp prediction. Preprint arXiv:2002.00872"},{"key":"9888_CR52","doi-asserted-by":"crossref","unstructured":"DeTone D, Malisiewicz T, Rabinovich A (2018) Superpoint: self-supervised interest point detection and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 224\u2013236","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"9888_CR53","doi-asserted-by":"crossref","unstructured":"Ding D, Liu YH, Wang MY (2001) On computing immobilizing grasps of 3-d curved objects. In: IEEE international symposium on computational intelligence in robotics and automation, IEEE, pp 11\u201316","DOI":"10.1109\/CIRA.2001.1013165"},{"key":"9888_CR54","unstructured":"Do TT, Cai M, Pham T, Reid I (2018) Deep-6dpose: recovering 6d object pose from a single rgb image. Preprint arXiv:1802.10367"},{"key":"9888_CR55","doi-asserted-by":"crossref","unstructured":"Do TT, Nguyen A, Reid I (2018) Affordancenet: an end-to-end deep learning approach for object affordance detection. In: 2018 IEEE international conference on robotics and automation (ICRA), IEEE, pp 1\u20135","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"9888_CR56","doi-asserted-by":"crossref","unstructured":"Domae Y, Okuda H, Taguchi Y, Sumi K, Hirai T (2014) Fast graspability evaluation on single depth maps for bin picking with general grippers. In: 2014 IEEE international conference on robotics and automation (ICRA), IEEE, pp. 1997\u20132004","DOI":"10.1109\/ICRA.2014.6907124"},{"key":"9888_CR57","doi-asserted-by":"crossref","unstructured":"Dong Z, Li G, Liao Y, Wang F, Ren P, Qian C (2020) Centripetalnet: pursuing high-quality keypoint pairs for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10519\u201310528","DOI":"10.1109\/CVPR42600.2020.01053"},{"issue":"2","key":"9888_CR58","first-page":"112","volume":"10","author":"DH Douglas","year":"1973","unstructured":"Douglas DH, Peucker TK (1973) Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartogr Int J Geogr Inf Geovis 10(2):112\u2013122","journal-title":"Cartogr Int J Geogr Inf Geovis"},{"key":"9888_CR59","doi-asserted-by":"crossref","unstructured":"Drost B, Ilic S (2012) 3d object detection and localization using multimodal point pair features. In: International conference on 3D imaging, modeling, processing, visualization transmission, pp 9\u201316","DOI":"10.1109\/3DIMPVT.2012.53"},{"key":"9888_CR60","doi-asserted-by":"crossref","unstructured":"Drost B, Ulrich M, Navab N, Ilic S (2010) Model globally, match locally: efficient and robust 3d object recognition. In: 2010 IEEE computer society conference on computer vision and pattern recognition, pp 998\u20131005","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"9888_CR61","doi-asserted-by":"crossref","unstructured":"Du L, Ye X, Tan X, Feng J, Xu Z, Ding E, Wen S (2020) Associate-3ddet: perceptual-to-conceptual association for 3d point cloud object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13329\u201313338","DOI":"10.1109\/CVPR42600.2020.01334"},{"key":"9888_CR62","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"9888_CR63","doi-asserted-by":"crossref","unstructured":"Engelmann F, Bokeloh M, Fathi A, Leibe B, Nie\u00dfner M (2020) 3d-mpa: multi-proposal aggregation for 3d semantic instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9031\u20139040","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"9888_CR64","doi-asserted-by":"crossref","unstructured":"Erhan D, Szegedy C, Toshev A, Anguelov D (2014) Scalable object detection using deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2147\u20132154","DOI":"10.1109\/CVPR.2014.276"},{"issue":"4","key":"9888_CR65","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1109\/TRO.2019.2914772","volume":"35","author":"P Falco","year":"2019","unstructured":"Falco P, Lu S, Natale C, Pirozzi S, Lee D (2019) A transfer learning approach to cross-modal object recognition: from visual observation to robotic haptic exploration. IEEE Trans Robot 35(4):987\u2013998","journal-title":"IEEE Trans Robot"},{"issue":"4","key":"9888_CR66","doi-asserted-by":"crossref","first-page":"3995","DOI":"10.1109\/LRA.2019.2928210","volume":"4","author":"Y Fan","year":"2019","unstructured":"Fan Y, Tomizuka M (2019) Efficient grasp planning and execution with multifingered hands by surface fitting. IEEE Robot Autom Lett 4(4):3995\u20134002","journal-title":"IEEE Robot Autom Lett"},{"key":"9888_CR67","doi-asserted-by":"crossref","unstructured":"Fan Z, Yu JG, Liang Z, Ou J, Gao C, Xia GS, Li Y (2020) Fgn: fully guided network for few-shot instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9172\u20139181","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"9888_CR68","doi-asserted-by":"crossref","unstructured":"Fang HS, Wang C, Gou M, Lu C (2020) Graspnet-1billion: a large-scale benchmark for general object grasping. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11444\u201311453","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"9888_CR69","doi-asserted-by":"crossref","unstructured":"Fang K, Bai Y, Hinterstoisser S, Savarese S, Kalakrishnan M (2018) Multi-task domain adaptation for deep learning of instance grasping from simulation. In: 2018 IEEE international conference on robotics and automation (ICRA), IEEE, pp 3516\u20133523","DOI":"10.1109\/ICRA.2018.8461041"},{"issue":"6","key":"9888_CR70","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381\u2013395","journal-title":"Commun ACM"},{"key":"9888_CR71","volume-title":"A buyer\u2019s guide to conic fitting","author":"AW Fitzgibbon","year":"1996","unstructured":"Fitzgibbon AW, Fisher RB et al (1996) A buyer\u2019s guide to conic fitting. Department of Artificial Intelligence, University of Edinburgh, Edinburgh"},{"key":"9888_CR72","unstructured":"Florence PR, Manuelli L, Tedrake R (2018) Dense object nets: learning dense visual object descriptors by and for robotic manipulation. Preprint arXiv:1806.08756"},{"key":"9888_CR73","doi-asserted-by":"crossref","unstructured":"Frome A, Huber D, Kolluri R, B\u00fclow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: European conference on computer vision, Springer, pp 224\u2013237","DOI":"10.1007\/978-3-540-24672-5_18"},{"key":"9888_CR74","doi-asserted-by":"crossref","unstructured":"Gao G, Lauri M, Wang Y, Hu X, Zhang J, Frintrop S (2020) 6d object pose regression via supervised learning on point clouds. Preprint arXiv:2001.08942","DOI":"10.1109\/ICRA40945.2020.9197461"},{"key":"9888_CR75","unstructured":"Gao W, Tedrake R (2019) kpam-sc: generalizable manipulation planning using keypoint affordance and shape completion. Preprint arXiv:1909.06980"},{"key":"9888_CR76","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"9888_CR77","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR \u201914, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"9888_CR78","doi-asserted-by":"crossref","unstructured":"Gojcic Z, Zhou C, Wegner JD, Wieser A (2019) The perfect match: 3d point cloud matching with smoothed densities. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5545\u20135554","DOI":"10.1109\/CVPR.2019.00569"},{"key":"9888_CR79","unstructured":"Gonzalez M, Kacete A, Murienne A, Marchand E (2020) Yoloff: you only learn offsets for robust 6dof object pose estimation. Preprint arXiv:2002.00911"},{"key":"9888_CR80","doi-asserted-by":"crossref","unstructured":"Gordo A, Almaz\u00e1n J, Revaud J, Larlus D (2016) Deep image retrieval: learning global representations for image search. In: European conference on computer vision, Springer, pp 241\u2013257","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"9888_CR81","unstructured":"Goron LC, Marton ZC, Lazea G, Beetz M (2012) Robustly segmenting cylindrical and box-like objects in cluttered scenes using depth cameras. In: ROBOTIK 2012; 7th German conference on robotics, VDE, pp 1\u20136"},{"key":"9888_CR82","doi-asserted-by":"crossref","unstructured":"Graham B, Engelcke M, van\u00a0der Maaten L (2018) 3d semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9224\u20139232","DOI":"10.1109\/CVPR.2018.00961"},{"key":"9888_CR83","doi-asserted-by":"crossref","unstructured":"Graham B, van\u00a0der Maaten L (2017) Submanifold sparse convolutional networks. Preprint arXiv:1706.01307","DOI":"10.1109\/CVPR.2018.00961"},{"key":"9888_CR84","unstructured":"Guo D, Kong T, Sun F, Liu H (2016) Object discovery and grasp detection with a shared convolutional neural network. In: IEEE international conference on robotics and automation (ICRA), IEEE, pp 2038\u20132043"},{"key":"9888_CR85","doi-asserted-by":"crossref","unstructured":"Guo D, Sun F, Liu H, Kong T, Fang B, Xi N (2017) A hybrid deep architecture for robotic grasp detection. In: 2017 IEEE international conference on robotics and automation (ICRA), IEEE, pp 1609\u20131614","DOI":"10.1109\/ICRA.2017.7989191"},{"issue":"11","key":"9888_CR86","doi-asserted-by":"crossref","first-page":"3159","DOI":"10.1109\/TCYB.2017.2761361","volume":"48","author":"F Guo","year":"2017","unstructured":"Guo F, Wang W, Shen J, Shao L, Yang J, Tao D, Tang YY (2017) Video saliency detection using object proposals. IEEE Trans Cybern 48(11):3159\u20133170","journal-title":"IEEE Trans Cybern"},{"issue":"1","key":"9888_CR87","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/s11263-015-0824-y","volume":"116","author":"Y Guo","year":"2016","unstructured":"Guo Y, Bennamoun M, Sohel F, Lu M, Wan J, Kwok NM (2016) A comprehensive performance evaluation of 3d local feature descriptors. Int J Comput Vis 116(1):66\u201389","journal-title":"Int J Comput Vis"},{"key":"9888_CR88","doi-asserted-by":"crossref","unstructured":"Guo Y, Wang H, Hu Q, Liu H, Liu L, Bennamoun M (2019) Deep learning for 3d point clouds: a survey. Preprint arXiv:1912.12033","DOI":"10.1109\/TPAMI.2020.3005434"},{"issue":"3","key":"9888_CR89","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s13735-020-00195-x","volume":"9","author":"AM Hafiz","year":"2020","unstructured":"Hafiz AM, Bhat GM (2020) A survey on instance segmentation: state of the art. Int J Multimed Inf Retr 9(3):171\u2013189","journal-title":"Int J Multimed Inf Retr"},{"key":"9888_CR90","doi-asserted-by":"crossref","unstructured":"Hagelskj\u00e6r F, Buch AG (2019) Pointposenet: accurate object detection and 6 dof pose estimation in point clouds. Preprint arXiv:1912.09057","DOI":"10.1109\/ICIP40778.2020.9191119"},{"issue":"1","key":"9888_CR91","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han J, Zhang D, Cheng G, Liu N, Xu D (2018) Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Process Mag 35(1):84\u2013100","journal-title":"IEEE Signal Process Mag"},{"key":"9888_CR92","doi-asserted-by":"crossref","unstructured":"Han L, Zheng T, Xu L, Fang L (2020) Occuseg: occupancy-aware 3d instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2940\u20132949","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"9888_CR93","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Girshick R, Malik J (2014) Simultaneous detection and segmentation. In: European conference on computer vision, Springer, pp 297\u2013312","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"9888_CR94","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick RB (2017) Mask r-cnn. IEEE International conference on computer vision (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"9888_CR95","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"9888_CR96","doi-asserted-by":"crossref","unstructured":"He Y, Sun W, Huang H, Liu J, Fan H, Sun J (2020) Pvn3d: a deep point-wise 3d keypoints voting network for 6dof pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11632\u201311641","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"9888_CR97","doi-asserted-by":"crossref","unstructured":"Hinterstoisser S, Lepetit V, Ilic S, Holzer S, Bradski G, Konolige K, Navab N (2012) Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Asian conference on computer vision, Springer, pp 548\u2013562","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"9888_CR98","doi-asserted-by":"crossref","unstructured":"Hinton GE, Krizhevsky A, Wang SD (2011) Transforming auto-encoders. In: International conference on artificial neural networks, Springer, pp 44\u201351","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"9888_CR99","doi-asserted-by":"crossref","unstructured":"Hodan T, Barath D, Matas J (2020) Epos: estimating 6d pose of objects with symmetries. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11703\u201311712","DOI":"10.1109\/CVPR42600.2020.01172"},{"key":"9888_CR100","doi-asserted-by":"crossref","unstructured":"Hoda\u0148 T, Haluza P, Obdr\u017e\u00e1lek \u0160, Matas J, Lourakis M, Zabulis X (2017) T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: IEEE winter conference on applications of computer vision (WACV)","DOI":"10.1109\/WACV.2017.103"},{"key":"9888_CR101","doi-asserted-by":"crossref","unstructured":"Hodan T, Kouskouridas R, Kim T, Tombari F, Bekris KE, Drost B, Groueix T, Walas K, Lepetit V, Leonardis A, Steger C, Michel F, Sahin C, Rother C, Matas J (2018) A summary of the 4th international workshop on recovering 6d object pose. CoRR abs\/1810.03758","DOI":"10.1007\/978-3-030-11009-3_36"},{"key":"9888_CR102","doi-asserted-by":"crossref","unstructured":"Hoda\u0148 T, Michel F, Brachmann E, Kehl W, GlentBuch A, Kraft D, Drost B, Vidal J, Ihrke S, Zabulis X et\u00a0al (2018) Bop: benchmark for 6d object pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp 19\u201334","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"9888_CR103","doi-asserted-by":"crossref","unstructured":"Hoda\u0148 T, Zabulis X, Lourakis M, Obdr\u017e\u00e1lek \u0160, Matas J (2015) Detection and fine 3d pose estimation of texture-less objects in rgb-d images. In: 2015 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 4421\u20134428","DOI":"10.1109\/IROS.2015.7354005"},{"key":"9888_CR104","doi-asserted-by":"crossref","unstructured":"Hogan FR, Ballester J, Dong S, Rodriguez A (2020) Tactile dexterity: manipulation primitives with tactile feedback. Preprint arXiv:2002.03236","DOI":"10.1109\/ICRA40945.2020.9196976"},{"key":"9888_CR105","doi-asserted-by":"crossref","unstructured":"Hou J, Dai A, Nie\u00dfner M (2019) 3d-sis: 3d semantic instance segmentation of rgb-d scans. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4421\u20134430","DOI":"10.1109\/CVPR.2019.00455"},{"key":"9888_CR106","doi-asserted-by":"crossref","unstructured":"Hou Q, Cheng MM, Hu X, Borji A, Tu Z, Torr PH (2017) Deeply supervised salient object detection with short connections. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3203\u20133212","DOI":"10.1109\/CVPR.2017.563"},{"key":"9888_CR107","doi-asserted-by":"crossref","unstructured":"Hu Y, Fua P, Wang W, Salzmann M (2020) Single-stage 6d object pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2930\u20132939","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"9888_CR108","doi-asserted-by":"crossref","unstructured":"Hu Y, Hugonot J, Fua P, Salzmann M (2019) Segmentation-driven 6d object pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3385\u20133394","DOI":"10.1109\/CVPR.2019.00350"},{"key":"9888_CR109","doi-asserted-by":"crossref","unstructured":"Jiang H, Wang J, Yuan Z, Wu Y, Zheng N, Li S (2013) Salient object detection: a discriminative regional feature integration approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2083\u20132090","DOI":"10.1109\/CVPR.2013.271"},{"key":"9888_CR110","doi-asserted-by":"crossref","unstructured":"Jiang H, Xiao J (2013) A linear approach to matching cuboids in rgbd images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2171\u20132178","DOI":"10.1109\/CVPR.2013.282"},{"key":"9888_CR111","doi-asserted-by":"crossref","unstructured":"Jiang Y, Moseson S, Saxena A (2011) Efficient grasping from rgbd images: learning using a new rectangle representation. In: IEEE international conference on robotics and automation, IEEE, pp 3304\u20133311","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"9888_CR112","unstructured":"Johnson AE (1997) Spin-images: a representation for 3-d surface matching"},{"key":"9888_CR113","doi-asserted-by":"crossref","unstructured":"Kaiser A, Ybanez\u00a0Zepeda JA, Boubekeur T (2019) A survey of simple geometric primitives detection methods for captured 3d data. In: Computer graphics forum, Wiley Online Library, vol\u00a038, pp 167\u2013196","DOI":"10.1111\/cgf.13451"},{"key":"9888_CR114","doi-asserted-by":"crossref","unstructured":"Kehl W, Manhardt F, Tombari F, Ilic S, Navab N (2017) Ssd-6d: making rgb-based 3d detection and 6d pose estimation great again. In: Proceedings of the IEEE international conference on computer vision, pp 1521\u20131529","DOI":"10.1109\/ICCV.2017.169"},{"key":"9888_CR115","doi-asserted-by":"crossref","unstructured":"Khan SH, He X, Bennamoun M, Sohel F, Togneri R (2015) Separating objects and clutter in indoor scenes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4603\u20134611","DOI":"10.1109\/CVPR.2015.7299091"},{"key":"9888_CR116","doi-asserted-by":"crossref","unstructured":"Kim G, Huber D, Hebert M (2008) Segmentation of salient regions in outdoor scenes using imagery and 3-d data. In: 2008 IEEE workshop on applications of computer vision, IEEE, pp 1\u20138","DOI":"10.1109\/WACV.2008.4544014"},{"key":"9888_CR117","doi-asserted-by":"crossref","unstructured":"Kirillov A, Wu Y, He K, Girshick R (2020) Pointrend: image segmentation as rendering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9799\u20139808","DOI":"10.1109\/CVPR42600.2020.00982"},{"issue":"3","key":"9888_CR118","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/BF02187843","volume":"7","author":"D Kirkpatrick","year":"1992","unstructured":"Kirkpatrick D, Mishra B, Yap CK (1992) Quantitative steinitz\u2019s theorems with applications to multifingered grasping. Discrete Comput Geom 7(3):295\u2013318","journal-title":"Discrete Comput Geom"},{"key":"9888_CR119","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems\u2014volume 1, NIPS\u201912, pp 1097\u20131105"},{"key":"9888_CR120","doi-asserted-by":"crossref","unstructured":"Kumra S, Joshi S, Sahin F (2019) Antipodal robotic grasping using generative residual convolutional neural network. Preprint arXiv:1909.04810","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"9888_CR121","doi-asserted-by":"crossref","unstructured":"Kumra S, Kanan C (2017) Robotic grasp detection using deep convolutional neural networks. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 769\u2013776","DOI":"10.1109\/IROS.2017.8202237"},{"key":"9888_CR122","doi-asserted-by":"crossref","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O (2019) Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12697\u201312705","DOI":"10.1109\/CVPR.2019.01298"},{"key":"9888_CR123","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"9888_CR124","doi-asserted-by":"crossref","unstructured":"Lee MA, Zhu Y, Srinivasan K, Shah P, Savarese S, Fei-Fei L, Garg A, Bohg J (2019) Making sense of vision and touch: self-supervised learning of multimodal representations for contact-rich tasks. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 8943\u20138950","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"9888_CR125","doi-asserted-by":"crossref","unstructured":"Lee Y, Park J (2020) Centermask: real-time anchor-free instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13906\u201313915","DOI":"10.1109\/CVPR42600.2020.01392"},{"issue":"4\u20135","key":"9888_CR126","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1177\/0278364914549607","volume":"34","author":"I Lenz","year":"2015","unstructured":"Lenz I, Lee H, Saxena A (2015) Deep learning for detecting robotic grasps. Int J Robot Res 34(4\u20135):705\u2013724","journal-title":"Int J Robot Res"},{"key":"9888_CR127","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-3-642-17319-6_13","volume-title":"Simulation, modeling, and programming for autonomous robots","author":"B Le\u00f3n","year":"2010","unstructured":"Le\u00f3n B, Ulbrich S, Diankov R, Puche G, Przybylski M, Morales A, Asfour T, Moisio S, Bohg J, Kuffner J, Dillmann R (2010) Opengrasp: a toolkit for robot grasping simulation. In: Ando N, Balakirsky S, Hemker T, Reggiani M, von Stryk O (eds) Simulation, modeling, and programming for autonomous robots. Springer, Berlin, pp 109\u2013120"},{"key":"9888_CR128","doi-asserted-by":"crossref","unstructured":"Lepetit V, Fua P et\u00a0al (2005) Monocular model-based 3d tracking of rigid objects: a survey. Found Trends\u00ae Comput Graph Vis 1(1):1\u201389","DOI":"10.1561\/0600000001"},{"issue":"2","key":"9888_CR129","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit V, Moreno-Noguer F, Fua P (2009) Epnp: an accurate o(n) solution to the pnp problem. IJCV 81(2):155\u2013166","journal-title":"IJCV"},{"key":"9888_CR130","doi-asserted-by":"crossref","unstructured":"Li G, Liu Z, Ye L, Wang Y, Ling H (2020) Cross-modal weighting network for rgb-d salient object detection","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"9888_CR131","doi-asserted-by":"crossref","unstructured":"Li Y, Qi H, Dai J, Ji X, Wei Y (2017) Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2359\u20132367","DOI":"10.1109\/CVPR.2017.472"},{"key":"9888_CR132","doi-asserted-by":"crossref","unstructured":"Li Y, Wang G, Ji X, Xiang Y, Fox D (2018) Deepim: deep iterative matching for 6d pose estimation. Lecture notes in computer science, pp 695\u2013711","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"9888_CR133","doi-asserted-by":"crossref","unstructured":"Li Z, Wang G, Ji X (2019) Cdpn: coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 7678\u20137687","DOI":"10.1109\/ICCV.2019.00777"},{"key":"9888_CR134","doi-asserted-by":"crossref","unstructured":"Liang H, Ma X, Li S, G\u00f6rner M, Tang S, Fang B, Sun F, Zhang J (2019) Pointnetgpd: detecting grasp configurations from point sets. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 3629\u20133635","DOI":"10.1109\/ICRA.2019.8794435"},{"key":"9888_CR135","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Chen Y, Hu R, Urtasun R (2019) Multi-task multi-sensor fusion for 3d object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7345\u20137353","DOI":"10.1109\/CVPR.2019.00752"},{"key":"9888_CR136","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"9888_CR137","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"9888_CR138","unstructured":"Liu C, Furukawa Y (2019) Masc: multi-scale affinity with sparse convolution for 3d instance segmentation. Preprint arXiv:1902.04478"},{"key":"9888_CR139","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.neucom.2018.12.061","volume":"337","author":"F Liu","year":"2019","unstructured":"Liu F, Fang P, Yao Z, Fan R, Pan Z, Sheng W, Yang H (2019) Recovering 6d object pose from rgb indoor image based on two-stage detection network withmulti-task loss. Neurocomputing 337:15\u201323","journal-title":"Neurocomputing"},{"issue":"2","key":"9888_CR140","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietik\u00e4inen M (2020) Deep learning for generic object detection: a survey. Int J Comput Vis 128(2):261\u2013318","journal-title":"Int J Comput Vis"},{"key":"9888_CR141","doi-asserted-by":"crossref","unstructured":"Liu M, Pan Z, Xu K, Ganguly K, Manocha D (2019) Generating grasp poses for a high-dof gripper using neural networks. Preprint arXiv:1903.00425","DOI":"10.1109\/IROS40897.2019.8968115"},{"key":"9888_CR142","doi-asserted-by":"crossref","unstructured":"Liu N, Han J (2016) Dhsnet: deep hierarchical saliency network for salient object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 678\u2013686","DOI":"10.1109\/CVPR.2016.80"},{"key":"9888_CR143","doi-asserted-by":"crossref","unstructured":"Liu N, Han J, Yang MH (2018) Picanet: learning pixel-wise contextual attention for saliency detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3089\u20133098","DOI":"10.1109\/CVPR.2018.00326"},{"key":"9888_CR144","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"9888_CR145","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"9888_CR146","doi-asserted-by":"crossref","unstructured":"Liu X, Jonschkowski R, Angelova A, Konolige K (2020) Keypose: multi-view 3d labeling and keypoint estimation for transparent objects. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11602\u201311610","DOI":"10.1109\/CVPR42600.2020.01162"},{"key":"9888_CR147","doi-asserted-by":"crossref","unstructured":"Liu Y, Zhang Q, Zhang D, Han J (2019) Employing deep part-object relationships for salient object detection. In: Proceedings of the IEEE international conference on computer vision, pp 1232\u20131241","DOI":"10.1109\/ICCV.2019.00132"},{"key":"9888_CR148","doi-asserted-by":"crossref","unstructured":"Liu Z, Zhao X, Huang T, Hu R, Zhou Y, Bai X (2020) Tanet: robust 3d object detection from point clouds with triple attention. In: AAAI, pp 11677\u201311684","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"9888_CR149","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"9888_CR150","doi-asserted-by":"crossref","unstructured":"Lou X, Yang Y, Choi C (2019) Learning to generate 6-dof grasp poses with reachability awareness. Preprint arXiv:1910.06404","DOI":"10.1109\/ICRA40945.2020.9197413"},{"key":"9888_CR151","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the international conference on computer vision-Volume 2, ICCV \u201999, p 1150","DOI":"10.1109\/ICCV.1999.790410"},{"key":"9888_CR152","doi-asserted-by":"crossref","unstructured":"Lu W, Wan G, Zhou Y, Fu X, Yuan P, Song S (2019) Deepicp: an end-to-end deep neural network for 3d point cloud registration. Preprint arXiv:1905.04153","DOI":"10.1109\/ICCV.2019.00010"},{"key":"9888_CR153","doi-asserted-by":"crossref","unstructured":"Lundell J, Verdoja F, Kyrki V (2019) Robust grasp planning over uncertain shape completions. Preprint arXiv:1903.00645","DOI":"10.1109\/IROS40897.2019.8967816"},{"key":"9888_CR154","unstructured":"Luo T, Mo K, Huang Z, Xu J, Hu S, Wang L, Su H (2020) Learning to group: a bottom-up framework for 3d part discovery in unseen categories. In: International conference on learning representations"},{"key":"9888_CR155","doi-asserted-by":"crossref","unstructured":"Mahajan M, Bhattacharjee T, Krishnan A, Shukla P, Nandi G (2020) Semi-supervised grasp detection by representation learning in a vector quantized latent space. Preprint arXiv:2001.08477","DOI":"10.1109\/SPCOM50965.2020.9179578"},{"key":"9888_CR156","doi-asserted-by":"crossref","unstructured":"Mahler J, Liang J, Niyaz S, Laskey M, Doan R, Liu X, Ojea JA, Goldberg K (2017) Dex-net 2.0: seep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics. CoRR arXiv:1703.09312","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"9888_CR157","doi-asserted-by":"crossref","unstructured":"Malisiewicz T, Gupta A, Efros AA (2011) Ensemble of exemplar-svms for object detection and beyond. In: 2011 International conference on computer vision, IEEE, pp 89\u201396","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"9888_CR158","doi-asserted-by":"crossref","unstructured":"Mellado N, Aiger D, Mitra NJ (2014) Super 4pcs fast global pointcloud registration via smart indexing. In: Computer graphics forum, Wiley Online Library, vol\u00a033, pp 205\u2013215","DOI":"10.1111\/cgf.12446"},{"key":"9888_CR159","doi-asserted-by":"crossref","unstructured":"Van\u00a0der Merwe M, Lu Q, Sundaralingam B, Matak M, Hermans T (2019) Learning continuous 3d reconstructions for geometrically aware grasping. Preprint arXiv:1910.00983","DOI":"10.1109\/ICRA40945.2020.9196981"},{"issue":"4","key":"9888_CR160","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/MRA.2004.1371616","volume":"11","author":"AT Miller","year":"2004","unstructured":"Miller AT, Allen PK (2004) Graspit! a versatile simulator for robotic grasping. IEEE Robot Autom Mag 11(4):110\u2013122","journal-title":"IEEE Robot Autom Mag"},{"key":"9888_CR161","first-page":"1824","volume":"2","author":"AT Miller","year":"2003","unstructured":"Miller AT, Knoop S, Christensen HI, Allen PK (2003) Automatic grasp planning using shape primitives. ICRA 2:1824\u20131829","journal-title":"ICRA"},{"key":"9888_CR162","doi-asserted-by":"crossref","unstructured":"Minaee S, Boykov Y, Porikli F, Plaza A, Kehtarnavaz N, Terzopoulos D (2020) Image segmentation using deep learning: a survey. Preprint arXiv:2001.05566","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"9888_CR163","doi-asserted-by":"crossref","unstructured":"Mirtich B, Canny J (1994) Easily computable optimum grasps in 2-d and 3-d. In: IEEE international conference on robotics and automation, IEEE, pp 739\u2013747","DOI":"10.1109\/ROBOT.1994.351399"},{"key":"9888_CR164","doi-asserted-by":"crossref","unstructured":"Morrison D, Corke P, Leitner J (2018) Closing the loop for robotic grasping: a real-time, generative grasp synthesis approach. Preprint arXiv:1804.05172","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"9888_CR165","doi-asserted-by":"crossref","unstructured":"Morrison D, Corke P, Leitner J (2019) Multi-view picking: next-best-view reaching for improved grasping in clutter. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 8762\u20138768","DOI":"10.1109\/ICRA.2019.8793805"},{"key":"9888_CR166","doi-asserted-by":"crossref","unstructured":"Mousavian A, Eppner C, Fox D (2019) 6-dof graspnet: variational grasp generation for object manipulation. In: Proceedings of the IEEE international conference on computer vision, pp 2901\u20132910","DOI":"10.1109\/ICCV.2019.00299"},{"issue":"5","key":"9888_CR167","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal R, Montiel JMM, Tardos JD (2015) Orb-slam: a versatile and accurate monocular slam system. IEEE Trans Robot 31(5):1147\u20131163","journal-title":"IEEE Trans Robot"},{"key":"9888_CR168","doi-asserted-by":"crossref","unstructured":"Murali A, Mousavian A, Eppner C, Paxton C, Fox D (2019) 6-dof grasping for target-driven object manipulation in clutter. Preprint arXiv:1912.03628","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"9888_CR169","doi-asserted-by":"crossref","unstructured":"Najibi M, Lai G, Kundu A, Lu Z, Rathod V, Funkhouser T, Pantofaru C, Ross D, Davis LS, Fathi A (2020) Dops: learning to detect 3d objects and predict their 3d shapes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11913\u201311922","DOI":"10.1109\/CVPR42600.2020.01193"},{"key":"9888_CR170","doi-asserted-by":"crossref","unstructured":"Nguyen VD (1987) Constructing stable grasps in 3d. In: IEEE international conference on robotics and automation, IEEE, vol\u00a04, pp 234\u2013239","DOI":"10.1109\/ROBOT.1987.1088008"},{"key":"9888_CR171","doi-asserted-by":"crossref","unstructured":"Ni P, Zhang W, Zhu X, Cao Q (2020) Pointnet++ grasping: learning an end-to-end spatial grasp generation algorithm from sparse point clouds. Preprint arXiv:2003.09644","DOI":"10.1109\/ICRA40945.2020.9196740"},{"key":"9888_CR172","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.robot.2015.04.002","volume":"70","author":"E Nikandrova","year":"2015","unstructured":"Nikandrova E, Kyrki V (2015) Category-based task specific grasping. Robot Auton Syst 70:25\u201335","journal-title":"Robot Auton Syst"},{"key":"9888_CR173","doi-asserted-by":"crossref","unstructured":"Oberweger M, Rad M, Lepetit V (2018) Making deep heatmaps robust to partial occlusions for 3d object pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp 119\u2013134","DOI":"10.1007\/978-3-030-01267-0_8"},{"key":"9888_CR174","doi-asserted-by":"crossref","unstructured":"Pang Y, Zhang L, Zhao X, Lu H (2020) Hierarchical dynamic filtering network for rgb-d salient object detection. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"9888_CR175","unstructured":"Park D, Chun SY (2018) Classification based grasp detection using spatial transformer network. Preprint arXiv:1803.01356"},{"key":"9888_CR176","unstructured":"Park D, Seo Y, Chun SY (2018) Real-time, highly accurate robotic grasp detection using fully convolutional neural network with rotation ensemble module. Preprint arXiv:1812.07762"},{"key":"9888_CR177","doi-asserted-by":"crossref","unstructured":"Park D, Seo Y, Shin D, Choi J, Chun SY (2019) A single multi-task deep neural network with post-processing for object detection with reasoning and robotic grasp detection. Preprint arXiv:1909.07050","DOI":"10.1109\/ICRA40945.2020.9197179"},{"key":"9888_CR178","doi-asserted-by":"crossref","unstructured":"Park K, Mousavian A, Xiang Y, Fox D (2020) Latentfusion: end-to-end differentiable reconstruction and rendering for unseen object pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10710\u201310719","DOI":"10.1109\/CVPR42600.2020.01072"},{"key":"9888_CR179","doi-asserted-by":"crossref","unstructured":"Park K, Patten T, Vincze M (2019) Pix2pose: pixel-wise coordinate regression of objects for 6d pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 7668\u20137677","DOI":"10.1109\/ICCV.2019.00776"},{"issue":"13\u201314","key":"9888_CR180","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1177\/0278364917735594","volume":"36","author":"A ten Pas","year":"2017","unstructured":"ten Pas A, Gualtieri M, Saenko K, Platt R (2017) Grasp pose detection in point clouds. Int J Rob Res 36(13\u201314):1455\u20131473","journal-title":"Int J Rob Res"},{"key":"9888_CR181","unstructured":"Pas At, Platt R (2015) Using geometry to detect grasps in 3d point clouds. Preprint arXiv:1501.03100"},{"key":"9888_CR182","doi-asserted-by":"crossref","unstructured":"Patil AV, Rabha P (2018) A survey on joint object detection and pose estimation using monocular vision. Preprint arXiv:1811.10216","DOI":"10.1051\/matecconf\/201927702029"},{"key":"9888_CR183","doi-asserted-by":"crossref","unstructured":"Patten T, Park K, Vincze M (2020) Dgcm-net: dense geometrical correspondence matching network for incremental experience-based robotic grasping. Preprint arXiv:2001.05279","DOI":"10.3389\/frobt.2020.00120"},{"issue":"4","key":"9888_CR184","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1109\/TPAMI.2016.2562626","volume":"39","author":"H Peng","year":"2016","unstructured":"Peng H, Li B, Ling H, Hu W, Xiong W, Maybank SJ (2016) Salient object detection via structured matrix decomposition. IEEE Trans Pattern Anal Mach Intell 39(4):818\u2013832","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR185","doi-asserted-by":"crossref","unstructured":"Peng H, Li B, Xiong W, Hu W, Ji R (2014) Rgbd salient object detection: a benchmark and algorithms. In: European conference on computer vision, Springer, pp 92\u2013109","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"9888_CR186","doi-asserted-by":"crossref","unstructured":"Peng S, Liu Y, Huang Q, Zhou X, Bao H (2019) Pvnet: pixel-wise voting network for 6dof pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4561\u20134570","DOI":"10.1109\/CVPR.2019.00469"},{"key":"9888_CR187","doi-asserted-by":"crossref","unstructured":"Pereira N, Alexandre LA (2019) Maskedfusion: mask-based 6d object pose estimation. Preprint arXiv:1911.07771","DOI":"10.1109\/ICMLA51294.2020.00021"},{"key":"9888_CR188","doi-asserted-by":"crossref","unstructured":"Pham QH, Nguyen T, Hua BS, Roig G, Yeung SK (2019) Jsis3d: joint semantic-instance segmentation of 3d point clouds with multi-task pointwise networks and multi-value conditional random fields. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8827\u20138836","DOI":"10.1109\/CVPR.2019.00903"},{"key":"9888_CR189","doi-asserted-by":"crossref","unstructured":"Pham QH, Uy MA, Hua BS, Nguyen DT, Roig G, Yeung SK (2020) Lcd: learned cross-domain descriptors for 2d\u20133d matching. In: AAAI, pp 11856\u201311864","DOI":"10.1609\/aaai.v34i07.6859"},{"key":"9888_CR190","doi-asserted-by":"crossref","unstructured":"Piao Y, Ji W, Li J, Zhang M, Lu H (2019) Depth-induced multi-scale recurrent attention network for saliency detection. In: Proceedings of the IEEE international conference on computer vision, pp 7254\u20137263","DOI":"10.1109\/ICCV.2019.00735"},{"key":"9888_CR191","unstructured":"Pinheiro PO, Collobert R, Doll\u00e1r P (2015) Learning to segment object candidates. In: Advances in neural information processing systems, pp 1990\u20131998"},{"key":"9888_CR192","doi-asserted-by":"crossref","unstructured":"Pinheiro PO, Lin TY, Collobert R, Doll\u00e1r P (2016) Learning to refine object segments. In: European conference on computer vision, Springer, pp 75\u201391","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"9888_CR193","doi-asserted-by":"crossref","unstructured":"Pinto L, Gupta A (2016) Supersizing self-supervision: learning to grasp from 50k tries and 700 robot hours. In: IEEE International conference on robotics and automation (ICRA), IEEE, pp 3406\u20133413","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"9888_CR194","doi-asserted-by":"crossref","unstructured":"Ponce J, Sullivan S, Boissonnat JD, Merlet JP (1993) On characterizing and computing three-and four-finger force-closure grasps of polyhedral objects. In: IEEE international conference on robotics and automation, IEEE, pp 821\u2013827","DOI":"10.1109\/ROBOT.1993.291933"},{"key":"9888_CR195","doi-asserted-by":"crossref","unstructured":"Qi CR, Chen X, Litany O, Guibas LJ (2020) Imvotenet: boosting 3d object detection in point clouds with image votes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4404\u20134413","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"9888_CR196","doi-asserted-by":"crossref","unstructured":"Qi CR, Litany O, He K, Guibas LJ (2019) Deep hough voting for 3d object detection in point clouds. In: Proceedings of the IEEE international conference on computer vision, pp 9277\u20139286","DOI":"10.1109\/ICCV.2019.00937"},{"key":"9888_CR197","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ (2018) Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 918\u2013927","DOI":"10.1109\/CVPR.2018.00102"},{"key":"9888_CR198","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652\u2013660"},{"key":"9888_CR199","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in neural information processing systems, pp 5099\u20135108"},{"key":"9888_CR200","doi-asserted-by":"crossref","unstructured":"Qi Q, Zhao S, Shen J, Lam KM (2019) Multi-scale capsule attention-based salient object detection with multi-crossed layer connections. In: 2019 IEEE international conference on multimedia and expo (ICME), IEEE, pp 1762\u20131767","DOI":"10.1109\/ICME.2019.00303"},{"key":"9888_CR201","unstructured":"Qin Y, Chen R, Zhu H, Song M, Xu J, Su H (2020) S4g: Amodal single-view single-shot se (3) grasp detection in cluttered scenes. In: Conference on robot learning, pp 53\u201365"},{"issue":"5","key":"9888_CR202","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TIP.2017.2682981","volume":"26","author":"L Qu","year":"2017","unstructured":"Qu L, He S, Zhang J, Tian J, Tang Y, Yang Q (2017) Rgbd salient object detection via deep fusion. IEEE Trans Image Process 26(5):2274\u20132285","journal-title":"IEEE Trans Image Process"},{"key":"9888_CR203","unstructured":"Rabbani T, Van Den\u00a0Heuvel F (2005) Efficient hough transform for automatic detection of cylinders in point clouds. Isprs Wg Iii\/3, Iii\/4 3:60\u201365"},{"key":"9888_CR204","doi-asserted-by":"crossref","unstructured":"Rad M, Lepetit V (2017) Bb8: a scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth. In: IEEE international conference on computer vision, pp 3828\u20133836","DOI":"10.1109\/ICCV.2017.413"},{"key":"9888_CR205","doi-asserted-by":"crossref","unstructured":"Redmon J, Angelova A (2015) Real-time grasp detection using convolutional neural networks. In: 2015 IEEE international conference on robotics and automation (ICRA), IEEE, pp 1316\u20131322","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"9888_CR206","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"9888_CR207","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"9888_CR208","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. Preprint arXiv:1804.02767"},{"key":"9888_CR209","doi-asserted-by":"crossref","unstructured":"Ren J, Gong X, Yu L, Zhou W, Ying\u00a0Yang M (2015) Exploiting global priors for rgb-d saliency detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 25\u201332","DOI":"10.1109\/CVPRW.2015.7301391"},{"key":"9888_CR210","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"issue":"2","key":"9888_CR211","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1109\/LRA.2016.2532924","volume":"1","author":"C Rennie","year":"2016","unstructured":"Rennie C, Shome R, Bekris KE, De Souza AF (2016) A dataset for improved rgbd-based object detection and pose estimation for warehouse pick-and-place. IEEE Robot Autom Lett 1(2):1179\u20131185","journal-title":"IEEE Robot Autom Lett"},{"key":"9888_CR212","doi-asserted-by":"crossref","unstructured":"Rosten E, Drummond T (2005) Fusing points and lines for high performance tracking. In: Tenth IEEE international conference on computer vision (ICCV\u201905) Volume 1, IEEE, vol\u00a02, pp 1508\u20131515","DOI":"10.1109\/ICCV.2005.104"},{"key":"9888_CR213","doi-asserted-by":"crossref","unstructured":"Rublee E, Rabaud V, Konolige K, Bradski G (2011) Orb: an efficient alternative to sift or surf. In: 2011 International conference on computer vision, IEEE, pp 2564\u20132571","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"9888_CR214","doi-asserted-by":"crossref","unstructured":"Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (fpfh) for 3d registration. In: IEEE international conference on robotics and automation, pp 3212\u20133217","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"9888_CR215","doi-asserted-by":"crossref","unstructured":"Rusu RB, Blodow N, Marton ZC, Beetz M (2009) Close-range scene segmentation and reconstruction of 3d point cloud maps for mobile manipulation in domestic environments. In: 2009 IEEE\/RSJ international conference on intelligent robots and systems, IEEE, pp 1\u20136","DOI":"10.1109\/IROS.2009.5354683"},{"key":"9888_CR216","unstructured":"Sabour S, Frosst N, Hinton G (2018) Matrix capsules with em routing. In: 6th international conference on learning representations, ICLR, pp 1\u201315"},{"key":"9888_CR217","unstructured":"Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Advances in neural information processing systems, pp 3856\u20133866"},{"issue":"3","key":"9888_CR218","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.robot.2011.07.016","volume":"60","author":"A Sahbani","year":"2012","unstructured":"Sahbani A, El-Khoury S, Bidaud P (2012) An overview of 3d object grasp synthesis algorithms. Robot Auton Syst 60(3):326\u2013336 Autonomous Grasping","journal-title":"Robot Auton Syst"},{"key":"9888_CR219","doi-asserted-by":"crossref","unstructured":"Sajjan SS, Moore M, Pan M, Nagaraja G, Lee J, Zeng A, Song S (2019) Cleargrasp: 3d shape estimation of transparent objects for manipulation. Preprint arXiv:1910.02550","DOI":"10.1109\/ICRA40945.2020.9197518"},{"key":"9888_CR220","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.cviu.2014.04.011","volume":"125","author":"S Salti","year":"2014","unstructured":"Salti S, Tombari F, Stefano LD (2014) Shot: Unique signatures of histograms for surface and texture description. Comput Vis Image Underst 125:251\u2013264","journal-title":"Comput Vis Image Underst"},{"issue":"7","key":"9888_CR221","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1177\/0278364918779698","volume":"37","author":"J Sanchez","year":"2018","unstructured":"Sanchez J, Corrales JA, Bouzgarrou BC, Mezouar Y (2018) Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey. Int J Robot Res 37(7):688\u2013716","journal-title":"Int J Robot Res"},{"key":"9888_CR222","unstructured":"Sarode V, Li X, Goforth H, Aoki Y, Dhagat A, Srivatsan RA, Lucey S, Choset H (2019) One framework to register them all: pointnet encoding for point cloud alignment. Preprint arXiv:1912.05766"},{"key":"9888_CR223","unstructured":"Sarode V, Li X, Goforth H, Aoki Y, Srivatsan RA, Lucey S, Choset H (2019) Pcrnet: point cloud registration network using pointnet encoding. Preprint arXiv:1908.07906"},{"key":"9888_CR224","doi-asserted-by":"crossref","unstructured":"Saxena A, Driemeyer J, Kearns J, Osondu C, Ng AY (2008a) Learning to grasp novel objects using vision. In: Experimental robotics, Springer, pp 33\u201342","DOI":"10.1007\/978-3-540-77457-0_4"},{"key":"9888_CR225","doi-asserted-by":"crossref","unstructured":"Saxena A, Driemeyer J, Ng AY (2008b) Robotic grasping of novel objects using vision. Int J Robot Res 27(2):157\u2013173","DOI":"10.1177\/0278364907087172"},{"key":"9888_CR226","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: integrated recognition, localization and detection using convolutional networks. Preprint arXiv:1312.6229"},{"issue":"4","key":"9888_CR227","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1109\/TPAMI.2015.2465960","volume":"38","author":"J Shi","year":"2015","unstructured":"Shi J, Yan Q, Xu L, Jia J (2015) Hierarchical image saliency detection on extended cssd. IEEE Trans Pattern Anal Mach Intell 38(4):717\u2013729","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR229","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li H (2019) Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013779","DOI":"10.1109\/CVPR.2019.00086"},{"key":"9888_CR228","doi-asserted-by":"crossref","unstructured":"Shi S, Wang Z, Shi J, Wang X, Li H (2020) From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. Preprint arXiv:1907.03670","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"9888_CR231","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R (2020) Point-gnn: graph neural network for 3d object detection in a point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1711\u20131719","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"9888_CR232","unstructured":"Simon M, Fischer K, Milz S, Witt CT, Gross HM (2020) Stickypillars: robust feature matching on point clouds using graph neural networks. Preprint arXiv:2002.03983"},{"key":"9888_CR233","doi-asserted-by":"crossref","unstructured":"Song C, Song J, Huang Q (2020) Hybridpose: 6d object pose estimation under hybrid representations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 431\u2013440","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"9888_CR234","doi-asserted-by":"crossref","unstructured":"Song S, Xiao J (2014) Sliding shapes for 3d object detection in depth images. In: European conference on computer vision, Springer, pp 634\u2013651","DOI":"10.1007\/978-3-319-10599-4_41"},{"key":"9888_CR235","doi-asserted-by":"crossref","unstructured":"Song S, Xiao J (2016) Deep sliding shapes for amodal 3d object detection in rgb-d images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 808\u2013816","DOI":"10.1109\/CVPR.2016.94"},{"key":"9888_CR236","doi-asserted-by":"crossref","unstructured":"Sultana F, Sufian A, Dutta P (2020) Evolution of image segmentation using deep convolutional neural network: a survey. Preprint arXiv:2001.04074","DOI":"10.1016\/j.knosys.2020.106062"},{"key":"9888_CR237","doi-asserted-by":"crossref","unstructured":"Sultana F, Sufian A, Dutta P (2020) A review of object detection models based on convolutional neural network. In: Intelligent computing: image processing based applications, Springer, pp 1\u201316","DOI":"10.1007\/978-981-15-4288-6_1"},{"key":"9888_CR238","doi-asserted-by":"crossref","unstructured":"Sundermeyer M, Marton ZC, Durner M, Brucker M, Triebel R (2018) Implicit 3d orientation learning for 6d object detection from rgb images. In: European conference on computer vision, Springer International Publishing, pp 712\u2013729","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"9888_CR239","doi-asserted-by":"crossref","unstructured":"Suzuki K, Yokota Y, Kanazawa Y, Takebayashi T (2020) Online self-supervised learning for object picking: detecting optimum grasping position using a metric learning approach. In: 2020 IEEE\/SICE international symposium on system integration (SII), IEEE, pp 205\u2013212","DOI":"10.1109\/SII46433.2020.9025845"},{"key":"9888_CR240","unstructured":"Szegedy C, Reed S, Erhan D, Anguelov D, Ioffe S (2014) Scalable, high-quality object detection. Preprint arXiv:1412.1441"},{"issue":"7","key":"9888_CR241","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1109\/TVCG.2012.310","volume":"19","author":"GK Tam","year":"2013","unstructured":"Tam GK, Cheng ZQ, Lai YK, Langbein FC, Liu Y, Marshall D, Martin RR, Sun XF, Rosin PL (2013) Registration of 3d point clouds and meshes: a survey from rigid to nonrigid. IEEE Trans Vis Comput Graph 19(7):1199\u20131217","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"9888_CR242","doi-asserted-by":"crossref","unstructured":"Tejani A, Tang D, Kouskouridas R, Kim TK (2014) Latent-class hough forests for 3d object detection and pose estimation. In: European conference on computer vision, Springer, pp 462\u2013477","DOI":"10.1007\/978-3-319-10599-4_30"},{"key":"9888_CR243","doi-asserted-by":"crossref","unstructured":"Tekin B, Sinha SN, Fua P (2018) Real-time seamless single shot 6d object pose prediction. In: IEEE conference on computer vision and pattern recognition, pp 292\u2013301","DOI":"10.1109\/CVPR.2018.00038"},{"key":"9888_CR244","doi-asserted-by":"crossref","unstructured":"Tian H, Wang C, Manocha D, Zhang X (2019) Transferring grasp configurations using active learning and local replanning. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 1622\u20131628","DOI":"10.1109\/ICRA.2019.8793796"},{"key":"9888_CR245","doi-asserted-by":"crossref","unstructured":"Tian M, Pan L, Ang\u00a0Jr MH, Lee G.H (2020) Robust 6d object pose estimation by learning rgb-d features. Preprint arXiv:2003.00188","DOI":"10.1109\/ICRA40945.2020.9197555"},{"key":"9888_CR246","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"9888_CR247","unstructured":"Tosun T, Yang D, Eisner B, Isler V, Lee D (2020) Robotic grasping through combined image-based grasp proposal and 3d reconstruction. Preprint arXiv:2003.01649"},{"key":"9888_CR248","unstructured":"Tremblay J, To T, Sundaralingam B, Xiang Y, Fox D, Birchfield S (2018) Deep object pose estimation for semantic robotic grasping of household objects. Preprint arXiv:1809.10790"},{"key":"9888_CR249","doi-asserted-by":"crossref","unstructured":"Truong P, Apostolopoulos S, Mosinska A, Stucky S, Ciller C, Zanet SD (2019) Glampoints: greedily learned accurate match points. In: Proceedings of the IEEE international conference on computer vision, pp 10732\u201310741","DOI":"10.1109\/ICCV.2019.01083"},{"issue":"2","key":"9888_CR250","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vis 104(2):154\u2013171","journal-title":"Int J Comput Vis"},{"issue":"10","key":"9888_CR251","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1109\/TPAMI.2004.92","volume":"26","author":"L Vacchetti","year":"2004","unstructured":"Vacchetti L, Lepetit V, Fua P (2004) Stable real-time 3d tracking using online and offline information. IEEE Trans Pattern Anal Mach Intell 26(10):1385\u20131391","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR252","doi-asserted-by":"crossref","unstructured":"Vahrenkamp N, Westkamp L, Yamanobe N, Aksoy EE, Asfour T (2016) Part-based grasp planning for familiar objects. In: IEEE-RAS 16th international conference on humanoid robots (Humanoids), IEEE, pp 919\u2013925","DOI":"10.1109\/HUMANOIDS.2016.7803382"},{"key":"9888_CR253","doi-asserted-by":"crossref","unstructured":"Varley J, DeChant C, Richardson A, Ruales J, Allen P (2017) Shape completion enabled robotic grasping. In: 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 2442\u20132447","DOI":"10.1109\/IROS.2017.8206060"},{"key":"9888_CR254","doi-asserted-by":"crossref","unstructured":"Vidal J, Lin C, Mart\u00ed R (2018) 6d pose estimation using an improved method based on point pair features. In: 4th international conference on control, automation and robotics (ICCAR), pp 405\u2013409","DOI":"10.1109\/ICCAR.2018.8384709"},{"key":"9888_CR255","doi-asserted-by":"crossref","unstructured":"Villena-Martinez V, Oprea S, Saval-Calvo M, Azorin-Lopez J, Fuster-Guillo A, Fisher RB (2020) When deep learning meets data alignment: a review on deep registration networks (drns). Preprint arXiv:2003.03167","DOI":"10.3390\/app10217524"},{"key":"9888_CR256","doi-asserted-by":"crossref","unstructured":"Vohra M, Prakash R, Behera L (2019) Real-time grasp pose estimation for novel objects in densely cluttered environment. In: 2019 28th IEEE international conference on robot and human interactive communication (RO-MAN), IEEE, pp 1\u20136","DOI":"10.1109\/RO-MAN46459.2019.8956438"},{"key":"9888_CR257","doi-asserted-by":"crossref","unstructured":"Wada K, Sucar E, James S, Lenton D, Davison AJ (2020) Morefusion: multi-object reasoning for 6d pose estimation from volumetric fusion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14540\u201314549","DOI":"10.1109\/CVPR42600.2020.01455"},{"key":"9888_CR258","doi-asserted-by":"crossref","unstructured":"Wang C, Mart\u00edn-Mart\u00edn R, Xu D, Lv J, Lu C, Fei-Fei L, Savarese S, Zhu Y (2019) 6-pack: category-level 6d pose tracker with anchor-based keypoints. Preprint arXiv:1910.10750","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"9888_CR259","doi-asserted-by":"crossref","unstructured":"Wang C, Xu D, Zhu Y, Mart\u00edn-Mart\u00edn R, Lu C, Fei-Fei L, Savarese S (2019) Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3343\u20133352","DOI":"10.1109\/CVPR.2019.00346"},{"key":"9888_CR260","doi-asserted-by":"crossref","unstructured":"Wang H, Sridhar S, Huang J, Valentin J, Song S, Guibas LJ (2019) Normalized object coordinate space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2642\u20132651","DOI":"10.1109\/CVPR.2019.00275"},{"key":"9888_CR261","doi-asserted-by":"crossref","unstructured":"Wang S, Jiang X, Zhao J, Wang X, Zhou W, Liu Y (2019) Efficient fully convolution neural network for generating pixel wise robotic grasps with high resolution images. In: 2019 IEEE international conference on robotics and biomimetics (ROBIO), IEEE, pp 474\u2013480","DOI":"10.1109\/ROBIO49542.2019.8961711"},{"key":"9888_CR262","doi-asserted-by":"crossref","unstructured":"Wang S, Wu J, Sun X, Yuan W, Freeman WT, Tenenbaum JB, Adelson EH (2018) 3d shape perception from monocular vision, touch, and shape priors. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 1606\u20131613","DOI":"10.1109\/IROS.2018.8593430"},{"key":"9888_CR263","unstructured":"Wang W, Lai Q, Fu H, Shen J, Ling H (2019) Salient object detection in the deep learning era: an in-depth survey. Preprint arXiv:1904.09146"},{"issue":"11","key":"9888_CR264","doi-asserted-by":"crossref","first-page":"5025","DOI":"10.1109\/TIP.2016.2601784","volume":"25","author":"W Wang","year":"2016","unstructured":"Wang W, Shen J, Shao L, Porikli F (2016) Correspondence driven saliency transfer. IEEE Trans Image Process 25(11):5025\u20135034","journal-title":"IEEE Trans Image Process"},{"key":"9888_CR265","doi-asserted-by":"crossref","unstructured":"Wang W, Yu R, Huang Q, Neumann U (2018) Sgpn: similarity group proposal network for 3d point cloud instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2569\u20132578","DOI":"10.1109\/CVPR.2018.00272"},{"key":"9888_CR266","unstructured":"Wang X, Kong T, Shen C, Jiang Y, Li L (2019) Solo: segmenting objects by locations. Preprint arXiv:1912.04488"},{"key":"9888_CR267","doi-asserted-by":"crossref","unstructured":"Wang X, Liu S, Shen X, Shen C, Jia J (2019) Associatively segmenting instances and semantics in point clouds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4096\u20134105","DOI":"10.1109\/CVPR.2019.00422"},{"key":"9888_CR268","doi-asserted-by":"crossref","unstructured":"Wang Y, Solomon JM (2019) Deep closest point: learning representations for point cloud registration. In: Proceedings of the IEEE international conference on computer vision, pp 3523\u20133532","DOI":"10.1109\/ICCV.2019.00362"},{"key":"9888_CR269","unstructured":"Wang Y, Solomon JM (2019) Prnet: self-supervised learning for partial-to-partial registration. In: Advances in neural information processing systems, pp 8812\u20138824"},{"key":"9888_CR270","doi-asserted-by":"crossref","unstructured":"Wang Z, Jia K (2019) Frustum convnet: sliding frustums to aggregate local point-wise features for amodal 3d object detection. In: 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 1742\u20131749","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"9888_CR271","doi-asserted-by":"crossref","unstructured":"Watkins-Valls D, Varley J, Allen P (2019) Multi-modal geometric learning for grasping and manipulation. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 7339\u20137345","DOI":"10.1109\/ICRA.2019.8794233"},{"key":"9888_CR272","doi-asserted-by":"crossref","unstructured":"Wei Y, Wen F, Zhu W, Sun J (2012) Geodesic saliency using background priors. In: European conference on computer vision, Springer, pp 29\u201342","DOI":"10.1007\/978-3-642-33712-3_3"},{"key":"9888_CR273","doi-asserted-by":"crossref","unstructured":"Wong JM, Kee V, Le T, Wagner S, Mariottini GL, Schneider A, Hamilton L, Chipalkatty R, Hebert M, Johnson DM, et\u00a0al (2017) Segicp: integrated deep semantic segmentation and pose estimation. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 5784\u20135789","DOI":"10.1109\/IROS.2017.8206470"},{"key":"9888_CR274","doi-asserted-by":"crossref","unstructured":"Xiang Y, Schmidt T, Narayanan V, Fox D (2018) Posecnn: a convolutional neural network for 6d object pose estimation in cluttered scenes. Preprint\narXiv:1711.00199","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"9888_CR275","unstructured":"Xie C, Xiang Y, Mousavian A, Fox D (2020) The best of both modes: separately leveraging rgb and depth for unseen object instance segmentation. In: Conference on robot learning, pp 1369\u20131378"},{"key":"9888_CR276","doi-asserted-by":"crossref","unstructured":"Xie E, Sun P, Song X, Wang W, Liu X, Liang D, Shen C, Luo P (2020) Polarmask: single shot instance segmentation with polar representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12193\u201312202","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"9888_CR277","doi-asserted-by":"crossref","unstructured":"Xie Q, Lai YK, Wu J, Wang Z, Zhang Y, Xu K, Wang J (2020) Mlcvnet: multi-level context votenet for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10447\u201310456","DOI":"10.1109\/CVPR42600.2020.01046"},{"key":"9888_CR278","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A (2018) Pointfusion: deep sensor fusion for 3d bounding box estimation. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00033"},{"key":"9888_CR279","unstructured":"Xue Z, Kasper A, Zoellner JM, Dillmann R (2009) An automatic grasp planning system for service robots. In: 2009 international conference on advanced robotics, IEEE, pp 1\u20136"},{"key":"9888_CR280","doi-asserted-by":"crossref","unstructured":"Yan X, Hsu J, Khansari M, Bai Y, Pathak A, Gupta A, Davidson J, Lee H (2018) Learning 6-dof grasping interaction via deep geometry-aware 3d representations. In: 2018 IEEE international conference on robotics and automation (ICRA), IEEE, pp 1\u20139","DOI":"10.1109\/ICRA.2018.8460609"},{"key":"9888_CR281","unstructured":"Yan X, Khansari M, Hsu J, Gong Y, Bai Y, Pirk S, Lee H (2019) Data-efficient learning for sim-to-real robotic grasping using deep point cloud prediction networks. Preprint arXiv:1906.08989"},{"issue":"10","key":"9888_CR282","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan Y, Mao Y, Li B (2018) Second: sparsely embedded convolutional detection. Sensors 18(10):3337","journal-title":"Sensors"},{"key":"9888_CR283","unstructured":"Yang B, Wang J, Clark R, Hu Q, Wang S, Markham A, Trigoni N (2019) Learning object bounding boxes for 3d instance segmentation on point clouds. In: Advances in neural information processing systems, pp 6737\u20136746"},{"key":"9888_CR284","doi-asserted-by":"crossref","unstructured":"Yang C, Zhang L, Lu H, Ruan X, Yang MH (2013) Saliency detection via graph-based manifold ranking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3166\u20133173","DOI":"10.1109\/CVPR.2013.407"},{"key":"9888_CR285","doi-asserted-by":"crossref","unstructured":"Yang H, Shi J, Carlone L (2020) Teaser: fast and certifiable point cloud registration. Preprint arXiv:2001.07715","DOI":"10.1109\/TRO.2020.3033695"},{"issue":"11","key":"9888_CR286","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1109\/TPAMI.2015.2513405","volume":"38","author":"J Yang","year":"2015","unstructured":"Yang J, Li H, Campbell D, Jia Y (2015) Go-icp: a globally optimal solution to 3d icp point-set registration. IEEE Trans Pattern Anal Mach Intell 38(11):2241\u20132254","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9888_CR287","doi-asserted-by":"crossref","unstructured":"Yang S, Zhang W, Lu W, Wang H, Li Y (2019) Learning actions from human demonstration video for robotic manipulation. Preprint arXiv:1909.04312","DOI":"10.1109\/IROS40897.2019.8968278"},{"key":"9888_CR288","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3dssd: point-based 3d single stage object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11040\u201311048","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"9888_CR289","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J (2019) Std: sparse-to-dense 3d object detector for point cloud. In: Proceedings of the IEEE international conference on computer vision, pp 1951\u20131960","DOI":"10.1109\/ICCV.2019.00204"},{"key":"9888_CR290","doi-asserted-by":"crossref","unstructured":"Ye M, Xu S, Cao T (2020) Hvnet: hybrid voxel network for lidar based 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1631\u20131640","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"9888_CR291","doi-asserted-by":"crossref","unstructured":"Yew ZJ, Lee GH (2018) 3dfeat-net: weakly supervised local 3d features for point cloud registration. In: European conference on computer vision, Springer, pp 630\u2013646","DOI":"10.1007\/978-3-030-01267-0_37"},{"key":"9888_CR292","doi-asserted-by":"crossref","unstructured":"Yi KM, Trulls E, Lepetit V, Fua P (2016) Lift: learned invariant feature transform. In: European conference on computer vision, Springer, pp 467\u2013483","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"9888_CR293","doi-asserted-by":"crossref","unstructured":"Yi L, Zhao W, Wang H, Sung M, Guibas LJ (2019) Gspn: generative shape proposal network for 3d instance segmentation in point cloud. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3947\u20133956","DOI":"10.1109\/CVPR.2019.00407"},{"key":"9888_CR294","doi-asserted-by":"crossref","unstructured":"Yokota Y, Suzuki K, Kanazawa Y, Takebayashi T (2020) A multi-task learning framework for grasping-position detection and few-shot classification. In: 2020 IEEE\/SICE international symposium on system integration (SII), IEEE, pp 1033\u20131039","DOI":"10.1109\/SII46433.2020.9025946"},{"key":"9888_CR295","doi-asserted-by":"crossref","unstructured":"Yu F, Liu K, Zhang Y, Zhu C, Xu K (2019) Partnet: a recursive part decomposition network for fine-grained and hierarchical shape segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9491\u20139500","DOI":"10.1109\/CVPR.2019.00972"},{"key":"9888_CR296","unstructured":"Yu P, Rao Y, Lu J, Zhou J (2019) P$$^{2}$$gnet: pose-guided point cloud generating networks for 6-dof object pose estimation. Preprint arXiv:1912.09316 (2019)"},{"key":"9888_CR297","unstructured":"Yu X, Zhuang Z, Koniusz P, Li H (2020) 6dof object pose estimation via differentiable proxy voting loss. Preprint arXiv:2002.03923"},{"key":"9888_CR298","doi-asserted-by":"crossref","unstructured":"Yuan Y, Hou J, N\u00fcchter A, Schwertfeger S (2020) Self-supervised point set local descriptors for point cloud registration. Preprint arXiv:2003.05199","DOI":"10.3390\/s21020486"},{"key":"9888_CR299","doi-asserted-by":"crossref","unstructured":"Zakharov S, Shugurov I, Ilic S (2019) Dpod: 6d pose object detector and refiner. In: Proceedings of the IEEE international conference on computer vision, pp 1941\u20131950","DOI":"10.1109\/ICCV.2019.00203"},{"issue":"1","key":"9888_CR300","doi-asserted-by":"crossref","first-page":"172988141983184","DOI":"10.1177\/1729881419831846","volume":"16","author":"BS Zapata-Impata","year":"2019","unstructured":"Zapata-Impata BS, Gil P, Pomares J, Torres F (2019) Fast geometry-based computation of grasping points on three-dimensional point clouds. Int J Adv Robot Syst 16(1):1729881419831846","journal-title":"Int J Adv Robot Syst"},{"key":"9888_CR301","doi-asserted-by":"crossref","unstructured":"Zapata-Impata BS, Mateo\u00a0Agull\u00f3 C, Gil P, Pomares J (2017) Using geometry to detect grasping points on 3d unknown point cloud","DOI":"10.5220\/0006470701540161"},{"key":"9888_CR302","doi-asserted-by":"crossref","unstructured":"Zeng A, Song S, Nie\u00dfner M, Fisher M, Xiao J, Funkhouser T (2017a) 3dmatch: learning local geometric descriptors from rgb-d reconstructions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1802\u20131811","DOI":"10.1109\/CVPR.2017.29"},{"key":"9888_CR304","doi-asserted-by":"crossref","unstructured":"Zeng A, Yu KT, Song S, Suo D, Walker E, Rodriguez A, Xiao J (2017b) Multi-view self-supervised deep learning for 6d pose estimation in the amazon picking challenge. In: IEEE international conference on robotics and automation (ICRA), IEEE, pp 1386\u20131383","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"9888_CR303","doi-asserted-by":"crossref","unstructured":"Zeng A, Song S, Yu KT, Donlon E, Hogan FR, Bauza M, Ma D, Taylor O, Liu M, Romo E, et\u00a0al (2018) Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching. In: IEEE international conference on robotics and automation (ICRA), IEEE, pp 1\u20138","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"9888_CR305","doi-asserted-by":"crossref","unstructured":"Zhang F, Guan C, Fang J, Bai S, Yang R, Torr P, Prisacariu V (2020) Instance segmentation of lidar point clouds. ICRA, Cited by 4(1)","DOI":"10.1109\/ICRA40945.2020.9196622"},{"key":"9888_CR306","doi-asserted-by":"crossref","unstructured":"Zhang H, Lan X, Bai S, Wan L, Yang C, Zheng N (2018) A multi-task convolutional neural network for autonomous robotic grasping in object stacking scenes. Preprint arXiv:1809.07081","DOI":"10.1109\/IROS40897.2019.8967977"},{"key":"9888_CR307","doi-asserted-by":"crossref","unstructured":"Zhang H, Lan X, Bai S, Zhou X, Tian Z, Zheng N (2018) Roi-based robotic grasp detection for object overlapping scenes. Preprint arXiv:1808.10313","DOI":"10.1109\/IROS40897.2019.8967869"},{"key":"9888_CR308","doi-asserted-by":"crossref","unstructured":"Zhang J, Sclaroff S, Lin Z, Shen X, Price B, Mech R (2016) Unconstrained salient object detection via proposal subset optimization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5733\u20135742","DOI":"10.1109\/CVPR.2016.618"},{"key":"9888_CR309","doi-asserted-by":"crossref","unstructured":"Zhang Q, Qu D, Xu F, Zou F (2017) Robust robot grasp detection in multimodal fusion. In: MATEC web of conferences, EDP Sciences, vol 139, p 00060","DOI":"10.1051\/matecconf\/201713900060"},{"key":"9888_CR310","doi-asserted-by":"crossref","unstructured":"Zhang Z, Sun B, Yang H, Huang Q (2020) H3dnet: 3d object detection using hybrid geometric primitives. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"9888_CR311","doi-asserted-by":"crossref","unstructured":"Zhao L, Tao W (2020) Jsnet: Joint instance and semantic segmentation of 3d point clouds. In: Thirty-Fourth AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v34i07.6994"},{"key":"9888_CR312","doi-asserted-by":"crossref","unstructured":"Zhao R, Ouyang W, Li H, Wang X (2015) Saliency detection by multi-context deep learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1265\u20131274","DOI":"10.1109\/CVPR.2015.7298731"},{"key":"9888_CR313","unstructured":"Zhao S, Li B, Xu P, Keutzer K (2020) Multi-source domain adaptation in the deep learning era: a systematic survey. Preprint arXiv:2002.12169"},{"issue":"11","key":"9888_CR314","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao ZQ, Zheng P, Xu S, Wu X (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30(11):3212\u20133232","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"9888_CR315","unstructured":"Zhao B, Zhang H, Lan X, Wang H, Tian Z, Zheng N (2020) Regnet: region-based grasp network for single-shot grasp detection in point clouds. Preprint arXiv:2002.12647"},{"key":"9888_CR316","doi-asserted-by":"crossref","unstructured":"Zheng T, Chen C, Yuan J, Li B, Ren K (2019) Pointcloud saliency maps. In: Proceedings of the IEEE international conference on computer vision, pp 1598\u20131606","DOI":"10.1109\/ICCV.2019.00168"},{"key":"9888_CR317","doi-asserted-by":"crossref","unstructured":"Zhou QY, Park J, Koltun V (2016) Fast global registration. In: European conference on computer vision, Springer, pp 766\u2013782","DOI":"10.1007\/978-3-319-46475-6_47"},{"key":"9888_CR318","doi-asserted-by":"crossref","unstructured":"Zhou X, Lan X, Zhang H, Tian Z, Zhang Y, Zheng N (2018) Fully convolutional grasp detection network with oriented anchor box. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 7223\u20137230","DOI":"10.1109\/IROS.2018.8594116"},{"key":"9888_CR319","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. Preprint arXiv:1904.07850"},{"key":"9888_CR320","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhuo J, Krahenbuhl P (2019) Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 850\u2013859","DOI":"10.1109\/CVPR.2019.00094"},{"key":"9888_CR321","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4490\u20134499","DOI":"10.1109\/CVPR.2018.00472"},{"key":"9888_CR322","doi-asserted-by":"crossref","unstructured":"Zhou Z, Pan T, Wu S, Chang H, Jenkins OC (2019) Glassloc: plenoptic grasp pose detection in transparent clutter. Preprint arXiv:1909.04269","DOI":"10.1109\/IROS40897.2019.8967685"},{"key":"9888_CR323","doi-asserted-by":"crossref","unstructured":"Zhu A, Yang J, Zhao C, Xian K, Cao Z, Li X (2020) Lrf-net: learning local reference frames for 3d local shape description and matching. Preprint arXiv:2001.07832","DOI":"10.3390\/s20185086"},{"key":"9888_CR324","doi-asserted-by":"crossref","unstructured":"Zhu W, Liang S, Wei Y, Sun J (2014) Saliency optimization from robust background detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2814\u20132821","DOI":"10.1109\/CVPR.2014.360"},{"key":"9888_CR325","unstructured":"Zou Z, Shi Z, Guo Y, Ye J (2019) Object detection in 20 years: a survey. Preprint arXiv:1905.05055"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-020-09888-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-020-09888-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-020-09888-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T23:40:09Z","timestamp":1629157209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-020-09888-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,17]]},"references-count":324,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["9888"],"URL":"https:\/\/doi.org\/10.1007\/s10462-020-09888-5","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,17]]},"assertion":[{"value":"17 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}