{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:45Z","timestamp":1740122925282,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16454-y","type":"journal-article","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T07:02:30Z","timestamp":1692255750000},"page":"25085-25103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Path aggregation one-stage anchor free 3D object detection"],"prefix":"10.1007","volume":"83","author":[{"given":"Yanfei","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4244-4032","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kanglin","family":"Ning","sequence":"additional","affiliation":[]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"key":"16454_CR1","unstructured":"Agarap AF (2018) Deep learning using rectified linear units (relu). ArXiv Prepr. ArXiv180308375"},{"key":"16454_CR2","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. ArXiv Prepr. ArXiv160706450"},{"key":"16454_CR3","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n J, Guindel C, Moreno FM, Cruzado D, Garcia F, De La Escalera A (2018) Birdnet: a 3d object detection framework from lidar information, in 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp 3517\u20133523","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"16454_CR4","unstructured":"Bhattacharyya P, Czarnecki K (2020) Deformable PV-RCNN: Improving 3D object detection with learned deformations. ArXiv Prepr. ArXiv200808766"},{"key":"16454_CR5","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. ArXiv Prepr. ArXiv200410934"},{"key":"16454_CR6","doi-asserted-by":"crossref","unstructured":"Cheng ZY, Liang J, Choi HJ, Tao GH, Cao ZW, Liu DF, Zhang XY (2022) Physical attack on monocular depth estimation with optimal adversarial patches 5. ArXiv abs\/2207.04718","DOI":"10.1007\/978-3-031-19839-7_30"},{"key":"16454_CR7","doi-asserted-by":"publisher","unstructured":"Cui YM, Yan LQ, Cao ZW, Liu DF (2021) TF-Blender: Temporal feature blender for video object detection. https:\/\/doi.org\/10.48550\/arXiv.2108.05821","DOI":"10.48550\/arXiv.2108.05821"},{"key":"16454_CR8","doi-asserted-by":"crossref","unstructured":"Deng J, Shi S, Li P, Zhou W, Zhang Y, Li H (2020) Voxel R-CNN: Towards high performance voxel-based 3D object detection. ArXiv Prepr. ArXiv201215712","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"16454_CR9","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Zhou Y, et al (2022) Scaling up your kernels to 31x31: Revisiting large kernel design in CNNs[J]. arXiv e-prints","DOI":"10.1109\/CVPR52688.2022.01166"},{"issue":"2","key":"16454_CR10","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S-H Gao","year":"2019","unstructured":"Gao S-H, Cheng M-M, Zhao K, Zhang X-Y, Yang M-H, Torr P (2019) Res2net: A new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell 43(2):652\u2013662","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16454_CR11","doi-asserted-by":"publisher","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun, R (2013) Vision meets robotics: the KITTI dataset. https:\/\/doi.org\/10.1177\/0278364913491297","DOI":"10.1177\/0278364913491297"},{"key":"16454_CR12","doi-asserted-by":"crossref","unstructured":"Godard C, Mac Aodha O, Firman M, Brostow G (2018) Digging into self-supervised monocular depth estimation 5. ArXiv.1806.01260","DOI":"10.1109\/ICCV.2019.00393"},{"key":"16454_CR13","doi-asserted-by":"crossref","unstructured":"He C, Zeng H, Huang J, Hua X-S, Zhang L (2020) Structure aware single-stage 3d object detection from point cloud, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11873\u201311882","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"16454_CR14","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":"16454_CR15","doi-asserted-by":"crossref","unstructured":"Hu Y et al. (2021) AFDetV2: Rethinking the necessity of the second stage for object detection from point clouds. ArXiv Prepr. ArXiv211209205","DOI":"10.1609\/aaai.v36i1.19980"},{"issue":"2","key":"16454_CR16","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/s004260050046","volume":"62","author":"GW Humphreys","year":"1999","unstructured":"Humphreys GW, Price CJ, Riddoch MJ (1999) From objects to names: A cognitive neuroscience approach. Psychol Res 62(2):118\u2013130","journal-title":"Psychol Res"},{"key":"16454_CR17","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization, ArXiv Prepr. ArXiv14126980"},{"key":"16454_CR18","doi-asserted-by":"publisher","unstructured":"Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-Normalizing Neural Networks. https:\/\/doi.org\/10.48550\/arXiv.1706.02515","DOI":"10.48550\/arXiv.1706.02515"},{"key":"16454_CR19","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\/CVF Conference on Computer Vision and Pattern Recognition, pp 12697\u201312705","DOI":"10.1109\/CVPR.2019.01298"},{"key":"16454_CR20","doi-asserted-by":"crossref","unstructured":"Li Z, Yao Y, Quan Z, Yang W, Xie J (2021) Sienet: spatial information enhancement network for 3d object detection from point cloud. ArXiv Prepr. ArXiv210315396","DOI":"10.1016\/j.patcog.2022.108684"},{"key":"16454_CR21","unstructured":"Liang J, Zhou TF, Liu DF, Wang WG (2023) CLUSTSEG: Clustering for Universal Segmentation 5. ArXiv abs\/2305.02187"},{"key":"16454_CR22","doi-asserted-by":"crossref","unstructured":"Lin T-Y, 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":"16454_CR23","doi-asserted-by":"crossref","unstructured":"Liu DF, Cui YM, Tan WB, Chen YJ (2021) Sg-net: Spatial granularity network for one-stage video instance segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9816\u20139825, June 7","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"16454_CR24","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"},{"issue":"7","key":"16454_CR25","first-page":"8","volume":"2","author":"Z Liu","year":"2021","unstructured":"Liu Z, Lin YT, Cao Y, Hu H, Wei YX, Zhang Z, Lin S, Guo BN (2021) Swin transformer: Hierarchical vision transformer using shifted windows. ICCV 2(7):8","journal-title":"ICCV"},{"key":"16454_CR26","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S (2022) A convnet for the 2020s, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11976\u201311986","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"16454_CR27","doi-asserted-by":"crossref","unstructured":"Mahmoud A, Hu JS, Waslander SL (2022) Dense voxel fusion for 3D object detection. ArXiv Prepr. ArXiv220300871","DOI":"10.1109\/WACV56688.2023.00073"},{"key":"16454_CR28","doi-asserted-by":"crossref","unstructured":"Pang S, Morris D, Radha H (2020) CLOCs: Camera-LiDAR object candidates fusion for 3D object detection, in 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 10386\u201310393","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"16454_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.algal.2020.101932","volume":"48","author":"G Pant","year":"2020","unstructured":"Pant G, Yadav D, Gaur A (2020) ResNeXt convolution neural network topology-based deep learning model for identification and classification of Pediastrum. Algal Res 48:101932","journal-title":"Algal Res"},{"key":"16454_CR30","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space, ArXiv Prepr. ArXiv170602413"},{"key":"16454_CR31","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":"16454_CR32","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement, ArXiv Prepr. ArXiv180402767"},{"key":"16454_CR33","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical image computing and computer-assisted intervention, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"16454_CR34","doi-asserted-by":"crossref","unstructured":"Shi S et al. (2020) Pv-rcnn: Point-voxel feature set abstraction for 3d object detection, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10529\u201310538","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"16454_CR35","doi-asserted-by":"crossref","unstructured":"Shi S et al. (2021) PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection, ArXiv Prepr. ArXiv210200463","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"16454_CR36","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\/CVF conference on computer vision and pattern recognition, pp 770\u2013779","DOI":"10.1109\/CVPR.2019.00086"},{"key":"16454_CR37","unstructured":"Shi S, Wang Z, Wang X, Li H (2019) Part-a\u02c6 2 net: 3d part-aware and aggregation neural network for object detection from point cloud 2(3). ArXiv Prepr. ArXiv190703670"},{"key":"16454_CR38","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. ArXiv Prepr. ArXiv14091556"},{"key":"16454_CR39","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2021) You only learn one representation: Unified network for multiple tasks. ArXiv Prepr. ArXiv210504206"},{"key":"16454_CR40","unstructured":"Wang WG, Han C, Zhou TF, Liu DF (2022) Visual recognition with deep nearest centroids 5. ArXiv preprint ArXiv:2209.07383"},{"key":"16454_CR41","unstructured":"Wang WG, Liang J, Liu DF (2022) Learning equivariant segmentation with instance-unique querying 10. ArXiv abs\/2210.00911"},{"key":"16454_CR42","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/S0079-6123(08)60487-2","volume":"75","author":"RE Weller","year":"1988","unstructured":"Weller RE (1988) Two cortical visual systems in old world and new world primates. Prog Brain Res 75:293\u2013306","journal-title":"Prog Brain Res"},{"key":"16454_CR43","doi-asserted-by":"crossref","unstructured":"Wu X et al (2022) Sparse fuse dense: Towards high quality 3D detection with depth completion. ArXiv Prepr. ArXiv220309780","DOI":"10.1109\/CVPR52688.2022.00534"},{"issue":"10","key":"16454_CR44","doi-asserted-by":"publisher","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":"16454_CR45","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":"16454_CR46","doi-asserted-by":"crossref","unstructured":"Yin T, Zhou X, Krahenbuhl P (2021) Center-based 3d object detection and tracking, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11784\u201311793","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"16454_CR47","doi-asserted-by":"crossref","unstructured":"Yin TW, Zhou XY, Kr\u00e4henb\u00fchl P (2020) Center-based 3D Object Detection and tracking. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11779-11788","DOI":"10.1109\/CVPR46437.2021.01161"},{"issue":"12","key":"16454_CR48","doi-asserted-by":"publisher","first-page":"10015","DOI":"10.1109\/TGRS.2019.2930982","volume":"57","author":"G Zhang","year":"2019","unstructured":"Zhang G, Lu S, Zhang W (2019) CAD-Net: A context-aware detection network for objects in remote sensing imagery. IEEE Trans Geosci Remote Sens 57(12):10015\u201310024","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"16454_CR49","doi-asserted-by":"crossref","unstructured":"Zhang R, Tang S, Liu L, Zhang Y, Li J, Yan S (2018) High resolution feature recovering for accelerating urban scene parsing, in IJCAI, pp 1156\u20131162","DOI":"10.24963\/ijcai.2018\/161"},{"key":"16454_CR50","doi-asserted-by":"crossref","unstructured":"Zheng W, Tang W, Chen S, Jiang L, Fu C-W (2020) CIA-SSD: Confident IoU-aware single-stage object detector from point cloud, ArXiv Prepr. ArXiv201203015","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"16454_CR51","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\/s11042-023-16454-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16454-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16454-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T13:44:15Z","timestamp":1708609455000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16454-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":51,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["16454"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16454-y","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,8,17]]},"assertion":[{"value":"17 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no known potential conflicts of interest with respect to financial interests or the research, authorship, and publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}