{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T11:18:13Z","timestamp":1766747893105,"version":"3.37.3"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T00:00:00Z","timestamp":1624579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T00:00:00Z","timestamp":1624579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100008569","name":"Oklahoma Center for the Advancement of Science and Technology","doi-asserted-by":"publisher","award":["HR12-030"],"award-info":[{"award-number":["HR12-030"]}],"id":[{"id":"10.13039\/100008569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R15 AG061833"],"award-info":[{"award-number":["R15 AG061833"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11042-021-11145-y","type":"journal-article","created":{"date-parts":[[2021,6,25]],"date-time":"2021-06-25T21:02:30Z","timestamp":1624654950000},"page":"35751-35773","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Holistic indoor scene understanding by context-supported instance segmentation"],"prefix":"10.1007","volume":"81","author":[{"given":"Lin","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8584-9040","authenticated-orcid":false,"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,25]]},"reference":[{"issue":"7","key":"11145_CR1","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/TMM.2017.2774007","volume":"20","author":"AH Abdulnabi","year":"2017","unstructured":"Abdulnabi AH, Shuai B, Zuo Z, Chau LP, Wang G (2017) Multimodal recurrent neural networks with information transfer layers for indoor scene labeling. IEEE Trans Multimed 20(7):1656\u20131671","journal-title":"IEEE Trans Multimed"},{"issue":"35","key":"11145_CR2","doi-asserted-by":"publisher","first-page":"25551","DOI":"10.1007\/s11042-020-09235-4","volume":"79","author":"M Bellver","year":"2020","unstructured":"Bellver M, Salvador A, Torres J, Giro-i Nieto X (2020) Mask-guided sample selection for semi-supervised instance segmentation. Multimed Tools Appl 79(35):25551\u201325569","journal-title":"Multimed Tools Appl"},{"key":"11145_CR3","doi-asserted-by":"crossref","unstructured":"Cabral R, Furukawa Y (2014) Piecewise planar and compact floorplan reconstruction from images. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2014.546"},{"key":"11145_CR4","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 CVPR","DOI":"10.1109\/CVPR.2017.691"},{"key":"11145_CR5","doi-asserted-by":"crossref","unstructured":"Choi MJ, Lim JJ, Torralba A, Willsky AS (2010) Exploiting hierarchical context on a large database of object categories. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2010.5540221"},{"issue":"2","key":"11145_CR6","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/TPAMI.2011.119","volume":"34","author":"MJ Choi","year":"2012","unstructured":"Choi MJ, Torralba A, Willsky AS (2012) A tree-based context model for object recognition. IEEE T-PAMI 34(2):240\u2013252","journal-title":"IEEE T-PAMI"},{"issue":"3","key":"11145_CR7","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TIT.1968.1054142","volume":"14","author":"C Chow","year":"1968","unstructured":"Chow C, Liu C (1968) Approximating discrete probability distributions with dependence trees. IEEE Trans Information Theory 14(3):462\u2013467","journal-title":"IEEE Trans Information Theory"},{"key":"11145_CR8","doi-asserted-by":"crossref","unstructured":"Dai A, Chang AX, Savva M, Halber M, Funkhouser T, Nie\u00dfner M (2017) Scannet: Richly-annotated 3D reconstructions of indoor scenes. In: Proceedings Computer vision and pattern recognition (CVPR). IEEE","DOI":"10.1109\/CVPR.2017.261"},{"key":"11145_CR9","doi-asserted-by":"crossref","unstructured":"Deng Z, Jan Latecki L (2017) Amodal detection of 3D objects: Inferring 3D bounding boxes from 2d ones in rgb-depth images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5762\u20135770","DOI":"10.1109\/CVPR.2017.50"},{"issue":"8","key":"11145_CR10","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1109\/TMM.2016.2572000","volume":"18","author":"X Ding","year":"2016","unstructured":"Ding X, Li B, Xiong W, Guo W, Hu W, Wang B (2016) Multi-instance multi-label learning combining hierarchical context and its application to image annotation. IEEE Trans Multimed 18(8):1616\u20131627","journal-title":"IEEE Trans Multimed"},{"issue":"8","key":"11145_CR11","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE T-PAMI 35(8):1915\u20131929","journal-title":"IEEE T-PAMI"},{"key":"11145_CR12","doi-asserted-by":"crossref","unstructured":"Furukawa Y, Curless B, S.M.S, Szeliski R (2009) Manhattan-world stereo. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2009.5206867"},{"issue":"19","key":"11145_CR13","doi-asserted-by":"publisher","first-page":"27383","DOI":"10.1007\/s11042-019-07858-w","volume":"78","author":"M Gao","year":"2019","unstructured":"Gao M, Du Y, Yang Y, Zhang J (2019) Adaptive anchor box mechanism to improve the accuracy in the object detection system. Multimed Tools Appl 78(19):27383\u201327402","journal-title":"Multimed Tools Appl"},{"key":"11145_CR14","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":"11145_CR15","doi-asserted-by":"crossref","unstructured":"Graham B, Engelcke M, Van der 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":"11145_CR16","doi-asserted-by":"crossref","unstructured":"Guo L, Fan G, Sheng W (2017) Robust object detection by cuboid matching with local plane optimization in indoor RGB-d images. In: Proceedings VCIP","DOI":"10.1109\/VCIP.2017.8305159"},{"key":"11145_CR17","doi-asserted-by":"crossref","unstructured":"Guo L, Fan G, Sheng W (2019) Dual graphical models for relational modeling of indoor object categories. In: Proceedings CVPR-workshops","DOI":"10.1109\/CVPRW.2019.00132"},{"key":"11145_CR18","doi-asserted-by":"crossref","unstructured":"Guo L, Fan G, Sheng W (2019) Creating 3D bounding box hypotheses from deep network Score-Maps. In: Proceedings ICIP","DOI":"10.1109\/ICIP.2019.8803081"},{"issue":"10","key":"11145_CR19","doi-asserted-by":"publisher","first-page":"4829","DOI":"10.1109\/TIP.2016.2599292","volume":"25","author":"M Hayat","year":"2016","unstructured":"Hayat M, Khan SH, Bennamoun M, An S (2016) A spatial layout and scale invariant feature representation for indoor scene classification. IEEE Trans Image Process 25(10):4829\u20134841","journal-title":"IEEE Trans Image Process"},{"key":"11145_CR20","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2016.90"},{"key":"11145_CR21","doi-asserted-by":"crossref","unstructured":"Ikehata S, Yang H, Furukawa Y (2015) Structured indoor modeling. In: Proceedings ICCV","DOI":"10.1109\/ICCV.2015.156"},{"issue":"3","key":"11145_CR22","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1109\/TMM.2016.2515367","volume":"18","author":"M Jian","year":"2016","unstructured":"Jian M, Jung C (2016) Semi-supervised bi-dictionary learning for image classification with smooth representation-based label propagation. IEEE Trans Multimed 18(3):458\u2013473","journal-title":"IEEE Trans Multimed"},{"issue":"2","key":"11145_CR23","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/TMM.2013.2291657","volume":"16","author":"M Jian","year":"2013","unstructured":"Jian M, Jung C, Zheng Y (2013) Discriminative structure learning for semantic concept detection with graph embedding. IEEE Trans Multimed 16(2):413\u2013426","journal-title":"IEEE Trans Multimed"},{"key":"11145_CR24","doi-asserted-by":"crossref","unstructured":"Jiang H, Xiao J (2013) A linear approach to matching cuboids in RGBD images. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2013.282"},{"key":"11145_CR25","unstructured":"Kohli YZMBP, Izadi S, Xiao J (2016) Deepcontext: Context-encoding neural pathways for 3D holistic scene understanding. arXiv:1603.04922"},{"key":"11145_CR26","doi-asserted-by":"crossref","unstructured":"Lahoud J, Ghanem B, Pollefeys M, Oswald MR (2019) 3D instance segmentation via multi-task metric learning","DOI":"10.1109\/ICCV.2019.00935"},{"issue":"7553","key":"11145_CR27","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436","journal-title":"Nature"},{"key":"11145_CR28","doi-asserted-by":"crossref","unstructured":"Lempitsky VS, Kohli P, Rother C, Sharp T (2009) Image segmentation with a bounding box prior. In: Proceedings ICCV","DOI":"10.1109\/ICCV.2009.5459262"},{"issue":"1","key":"11145_CR29","first-page":"191","volume":"124","author":"RM Lewis","year":"2000","unstructured":"Lewis RM, Torczon V, Trosset MW (2000) Direct search methods: then and now. JCAM 124(1):191\u2013 207","journal-title":"JCAM"},{"key":"11145_CR30","doi-asserted-by":"crossref","unstructured":"Li W, Gu J, Dong Y, Dong Y, Han J (2019) Indoor scene understanding via rgb-d image segmentation employing depth-based CNN and CRFs. Multimed Tools Appl 1\u201315","DOI":"10.1007\/s11042-019-07882-w"},{"issue":"4","key":"11145_CR31","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/TMM.2018.2867720","volume":"21","author":"Y Li","year":"2018","unstructured":"Li Y, Guo Y, Guo J, Ma Z, Kong X, Liu Q (2018) Joint CRF and locality-consistent dictionary learning for semantic segmentation. IEEE Trans Multimed 21(4):875\u2013886","journal-title":"IEEE Trans Multimed"},{"key":"11145_CR32","doi-asserted-by":"crossref","unstructured":"Li Z, Gan Y, Liang X, Yu Y, Cheng H, Lin L (2016) LSTM-CF: Unifying Context modeling and fusion with LSTMs for RGB-d scene labeling. In: Proceedings ECCV","DOI":"10.1007\/978-3-319-46475-6_34"},{"key":"11145_CR33","doi-asserted-by":"crossref","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2018) Detnet: A backbone network for object detection. arXiv:1804.06215","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"11145_CR34","unstructured":"Liu C, Furukawa Y (2019) Masc: Multi-scale affinity with sparse convolution for 3D instance segmentation. arXiv:1902.04478"},{"issue":"2","key":"11145_CR35","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s11042-014-1967-5","volume":"74","author":"Y Liu","year":"2015","unstructured":"Liu Y, Li Z, Liu J, Lu H (2015) Boosted miml method for weakly-supervised image semantic segmentation. Multimed Tools Appl 74(2):543\u2013559","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"11145_CR36","doi-asserted-by":"publisher","first-page":"4273","DOI":"10.1007\/s11042-016-3375-5","volume":"76","author":"X Lv","year":"2017","unstructured":"Lv X, Liu X, Li X, Li X, Jiang S, He Z (2017) Modality-specific and hierarchical feature learning for RGB-d hand-held object recognition. Multimed Tools Appl 76(3):4273\u20134290","journal-title":"Multimed Tools Appl"},{"key":"11145_CR37","doi-asserted-by":"crossref","unstructured":"Narita G, Seno T, Ishikawa T, Kaji Y (2019) Panopticfusion: Online volumetric semantic mapping at the level of stuff and things. In: Proceedings IROS","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"11145_CR38","doi-asserted-by":"crossref","unstructured":"Pinheiro PO, Collobert R (2015) From image-level to pixel-level labeling with convolutional networks. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"11145_CR39","doi-asserted-by":"crossref","unstructured":"Qi CR, Litany O, He K, Guibas LJ (2019) Deep hough voting for 3D object detection in point clouds. arXiv:1904.09664","DOI":"10.1109\/ICCV.2019.00937"},{"key":"11145_CR40","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 CVPR","DOI":"10.1109\/CVPR.2018.00102"},{"key":"11145_CR41","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 CVPR","DOI":"10.1109\/CVPR.2016.91"},{"key":"11145_CR42","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"},{"key":"11145_CR43","doi-asserted-by":"crossref","unstructured":"Ren Z, Sudderth EB (2016) Three-dimensional object detection and layout prediction using clouds of oriented gradients. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2016.169"},{"issue":"11","key":"11145_CR44","doi-asserted-by":"publisher","first-page":"6091","DOI":"10.1007\/s11042-014-2434-z","volume":"75","author":"CX Ries","year":"2016","unstructured":"Ries CX, Richter F, Lienhart R (2016) Towards automatic bounding box annotations from weakly labeled images. Multimed Tools Appl 75 (11):6091\u20136118","journal-title":"Multimed Tools Appl"},{"key":"11145_CR45","doi-asserted-by":"crossref","unstructured":"Shaikh RA, Memon I, Hussain R, Maitlo A, Shaikh H (2018) A contemporary approach for object recognition based on spatial layout and low level features\u2019 integration. Multimed Tools Appl 1\u201324","DOI":"10.1007\/s11042-018-6796-5"},{"key":"11145_CR46","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from RGBD images. In: Psongroc. ECCV. Springer","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"11145_CR47","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) SUN RGB-D: a RGB-d scene understanding benchmark suite. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"11145_CR48","doi-asserted-by":"crossref","unstructured":"Song S, Xiao J (2016) Deep sliding shapes for amodal 3D object detection in RGB-d images. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2016.94"},{"key":"11145_CR49","doi-asserted-by":"crossref","unstructured":"Song S, Zeng A, Chang AX, Savva M, Savarese S, Funkhouser T (2018) Im2pano3d: Extrapolating 360 structure and semantics beyond the field of view. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2018.00405"},{"key":"11145_CR50","doi-asserted-by":"crossref","unstructured":"Tang S, Wang X, Lv X, Han TX, Keller J, He Z, Skubic M, Lao S (2012) Histogram of oriented normal vectors for object recognition with a depth sensor. In: Proceedings ACCV","DOI":"10.1007\/978-3-642-37444-9_41"},{"issue":"16","key":"11145_CR51","doi-asserted-by":"publisher","first-page":"21185","DOI":"10.1007\/s11042-017-5576-y","volume":"77","author":"L Wu","year":"2018","unstructured":"Wu L, Liu Z, Song H, Le Meur O (2018) RGBD Co-saliency detection via multiple kernel boosting and fusion. Multimed Tools Appl 77(16):21185\u201321199","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"11145_CR52","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s11263-014-0711-y","volume":"110","author":"J Xiao","year":"2014","unstructured":"Xiao J, Furukawa Y (2014) Reconstructing the world\u2019s museums. IJCV 110(3):243\u2013258","journal-title":"IJCV"},{"key":"11145_CR53","doi-asserted-by":"crossref","unstructured":"Xiao J, Hays J, Ehinger KA, Oliva A, Torralba A (2010) SUN Database: Large-scale scene recognition from abbey to zoo. In: 2010 IEEE Computer society conference on computer vision and pattern recognition. IEEE, pp 3485\u20133492","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"11145_CR54","doi-asserted-by":"crossref","unstructured":"Xiao Z, Gao J, Wu D, Zhang L, Chen X (2020) A fast 3D object recognition algorithm using plane-constrained point pair features. Multimed Tools Appl 1\u201321","DOI":"10.1007\/s11042-020-09525-x"},{"key":"11145_CR55","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A (2018) Pointfusion: Deep sensor fusion for 3D bounding box estimation. In: Proceedings CVPR","DOI":"10.1109\/CVPR.2018.00033"},{"key":"11145_CR56","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: Proceedings NIPS"},{"issue":"10","key":"11145_CR57","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TMM.2018.2812605","volume":"20","author":"J Zhang","year":"2018","unstructured":"Zhang J, Wu Q, Shen C, Zhang J, Lu J (2018) Multilabel image classification with regional latent semantic dependencies. IEEE Trans Multimed 20 (10):2801\u20132813","journal-title":"IEEE Trans Multimed"},{"key":"11145_CR58","doi-asserted-by":"crossref","unstructured":"Zhang Y, Davison BD (2020) Domain adaptation for object recognition using subspace sampling demons. Multimed Tools Appl 1\u201320","DOI":"10.1007\/s11042-020-09336-0"},{"issue":"3","key":"11145_CR59","doi-asserted-by":"publisher","first-page":"4427","DOI":"10.1007\/s11042-016-3423-1","volume":"76","author":"Y Zheng","year":"2017","unstructured":"Zheng Y, Gao X (2017) Indoor scene recognition via multi-task metric multi-kernel learning from rgb-d images. Multimed Tools Appl 76(3):4427\u20134443","journal-title":"Multimed Tools Appl"},{"key":"11145_CR60","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"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11145-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11145-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11145-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T18:05:12Z","timestamp":1725300312000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11145-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,25]]},"references-count":60,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["11145"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11145-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,6,25]]},"assertion":[{"value":"6 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}