{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:30:34Z","timestamp":1768869034039,"version":"3.49.0"},"reference-count":103,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2017YFA070080"],"award-info":[{"award-number":["2017YFA070080"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11263-023-01807-9","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T02:01:37Z","timestamp":1686967297000},"page":"2665-2681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["InstaBoost++: Visual Coherence Principles for Unified 2D\/3D Instance Level Data Augmentation"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1030-5575","authenticated-orcid":false,"given":"Jianhua","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runzhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"1807_CR1","unstructured":"Arnheim, R. (1969). Visual thinking."},{"key":"1807_CR2","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., & Ferrari, V., et\u00a0al. (2016). What\u2019s the point: Semantic segmentation with point supervision. In ECCV.","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"1807_CR3","doi-asserted-by":"crossref","unstructured":"Bertalmio, M., Bertozzi, A.L., & Sapiro, G. (2001). Navier\u2013Stokes, fluid dynamics, and image and video inpainting. In CVPR.","DOI":"10.1109\/CVPR.2001.990497"},{"key":"1807_CR4","doi-asserted-by":"crossref","unstructured":"Bleau, A., & Leon, L.J. (2000). Watershed-based segmentation and region merging. In Computer vision and image understanding.","DOI":"10.1006\/cviu.1999.0822"},{"key":"1807_CR5","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., & Xiao, F., et\u00a0al. (2019). Yolact: Real-time instance segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9157\u20139166).","DOI":"10.1109\/ICCV.2019.00925"},{"key":"1807_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade R-CNN: Delving into high quality object detection. In CVPR.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1807_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., & Synnaeve, G., et\u00a0al. (2020). End-to-end object detection with transformers. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16 (pp 213\u2013229). Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1807_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Hermans, A., & Papandreou, G., et\u00a0al. (2018). Masklab: Instance segmentation by refining object detection with semantic and direction features. In CVPR.","DOI":"10.1109\/CVPR.2018.00422"},{"key":"1807_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., & Wan, J., et\u00a0al. (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"},{"key":"1807_CR10","unstructured":"Chen, K., Pang, J., & Wang, J., et\u00a0al. (2018). mmdetection. https:\/\/github.com\/open-mmlab\/mmdetection."},{"key":"1807_CR11","unstructured":"Chen, T., Saxena, S., & Li, L., et\u00a0al. (2021). Pix2seq: A language modeling framework for object detection. In International conference on learning representations."},{"key":"1807_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., & Schwing, A.G, et\u00a0al. (2022). Masked-attention mask transformer for universal image segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1290\u20131299).","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"1807_CR13","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., & Ramos, S., et\u00a0al. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1807_CR14","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., & Savva, M., et\u00a0al. (2017). Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5828\u20135839).","DOI":"10.1109\/CVPR.2017.261"},{"key":"1807_CR15","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Li, Y., et\u00a0al. (2016). Instance-sensitive fully convolutional networks. In ECCV.","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"1807_CR16","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Sun, J. (2015). Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2015.191"},{"key":"1807_CR17","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Sun, J. (2016). Instance-aware semantic segmentation via multi-task network cascades. In CVPR.","DOI":"10.1109\/CVPR.2016.343"},{"key":"1807_CR18","unstructured":"Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2016). Density estimation using real NVP. arXiv preprint arXiv:1605.08803."},{"key":"1807_CR19","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J., & Schmid, C. (2018). Modeling visual context is key to augmenting object detection datasets. In ECCV.","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"1807_CR20","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Misra, I., & Hebert, M. (2017). Cut, paste and learn: Surprisingly easy synthesis for instance detection. In ICCV.","DOI":"10.1109\/ICCV.2017.146"},{"key":"1807_CR21","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., & Williams, C.K., et\u00a0al. (2010). The pascal visual object classes (voc) challenge. IJCV.","DOI":"10.1007\/s11263-009-0275-4"},{"key":"1807_CR22","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Sun, J., & Wang, R., et\u00a0al. (2019). Instaboost: Boosting instance segmentation via probability map guided copy-pasting. In Proceedings of the IEEE international conference on computer vision (pp. 682\u2013691).","DOI":"10.1109\/ICCV.2019.00077"},{"key":"1807_CR23","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., & Tai, Y.W., et\u00a0al. (2017). Rmpe: Regional multi-person pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2017.256"},{"key":"1807_CR24","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., & Wang, X., et\u00a0al. (2021). Instances as queries. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6910\u20136919).","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"1807_CR25","doi-asserted-by":"crossref","unstructured":"Field, D.J., Hayes, A., & Hess, R.F. (1993). Contour integration by the human visual system: evidence for a local \u201cassociation field\u201d. Vision Research.","DOI":"10.1016\/0042-6989(93)90156-Q"},{"key":"1807_CR26","unstructured":"Ge, Z., Liu, S., & Wang, F., et\u00a0al. (2021). Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430."},{"key":"1807_CR27","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Cui, Y., & Srinivas, A., et\u00a0al. (2021). Simple copy-paste is a strong data augmentation method for instance segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"1807_CR28","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In ICCV.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1807_CR29","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., & Darrell, T., et\u00a0al. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2014.81"},{"key":"1807_CR30","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., & Zhang, D., et\u00a0al. (2017). Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing. In CVPR.","DOI":"10.1109\/CVPR.2017.715"},{"issue":"11","key":"1807_CR31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139\u2013144.","journal-title":"Communications of the ACM"},{"key":"1807_CR32","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbelaez, P., & Bourdev, L., et\u00a0al. (2011). Semantic contours from inverse detectors. In ICCV.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1807_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., & Doll\u00e1r, P., et\u00a0al. (2017). Mask r-cnn. In ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1807_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Rhemann, C., & Rother, C., et\u00a0al. (2011). A global sampling method for alpha matting. In CVPR.","DOI":"10.1109\/CVPR.2011.5995495"},{"key":"1807_CR35","first-page":"1","volume":"1","author":"A Khoreva","year":"2018","unstructured":"Khoreva, A., Benenson, R., Ilg, E., et al. (2018). Lucid data dreaming for video object segmentation. International Journal of Computer Vision, 1, 1\u201323.","journal-title":"International Journal of Computer Vision"},{"key":"1807_CR36","unstructured":"Kingma, D.P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114."},{"key":"1807_CR37","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., & Girshick, R., et\u00a0al. (2019). Panoptic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9404\u20139413).","DOI":"10.1109\/CVPR.2019.00963"},{"key":"1807_CR38","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., & He, K., et\u00a0al. (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"},{"key":"1807_CR39","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., & Lee, J., et\u00a0al. (2018). Joint 3d proposal generation and object detection from view aggregation. In 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp 1\u20138). IEEE.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"1807_CR40","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., & Caesar, H., et\u00a0al. (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":"1807_CR41","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":"1807_CR42","doi-asserted-by":"crossref","unstructured":"Leng, Z., Cheng, S., & Caine, B., et\u00a0al. (2022). Pseudoaugment: Learning to use unlabeled data for data augmentation in point clouds. In European conference on computer vision (pp. 555\u2013572). Springer.","DOI":"10.1007\/978-3-031-19821-2_32"},{"key":"1807_CR43","doi-asserted-by":"crossref","unstructured":"Li, Q., Arnab, A., & Torr, P.H. (2018). Weakly-and semi-supervised panoptic segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 102\u2013118).","DOI":"10.1007\/978-3-030-01267-0_7"},{"key":"1807_CR44","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., & Zhu, Z., et\u00a0al. (2019). Attention-guided unified network for panoptic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7026\u20137035).","DOI":"10.1109\/CVPR.2019.00719"},{"key":"1807_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., & Dai, J., et\u00a0al. (2017). Fully convolutional instance-aware semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2017.472"},{"key":"1807_CR46","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., & Zhu, H., et\u00a0al. (2019). Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. In CVPR.","DOI":"10.1109\/CVPR.2019.01112"},{"key":"1807_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y.L., Xu, L., & Liu, X., et\u00a0al. (2020). Pastanet: Toward human activity knowledge engine. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"1807_CR48","doi-asserted-by":"crossref","unstructured":"Li, Y.L., Zhou, S., & Huang, X., et\u00a0al. (2019). Transferable interactiveness knowledge for human-object interaction detection. In CVPR.","DOI":"10.1109\/CVPR.2019.00370"},{"key":"1807_CR49","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., & Wang, S., et\u00a0al. (2018). Deep continuous fusion for multi-sensor 3d object detection. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 641\u2013656).","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"1807_CR50","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., & Jia, J., et\u00a0al. (2016). Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2016.344"},{"key":"1807_CR51","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., & Girshick, R., et\u00a0al. (2017). Feature pyramid networks for object detection. In CVPR.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1807_CR52","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire. M., & Belongie. S, et\u00a0al. (2014). Microsoft coco: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1807_CR53","unstructured":"Lin, L., Xu, Y., & Liang, X., et\u00a0al. (2014). Complex background subtraction by pursuing dynamic spatio-temporal models. TIP."},{"key":"1807_CR54","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., & Erhan, D., et\u00a0al. (2016). Ssd: Single shot multibox detector. In ECCV.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1807_CR55","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., & Ma, C., et\u00a0al. (2019). See more, know more: Unsupervised video object segmentation with co-attention siamese networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00374"},{"key":"1807_CR56","unstructured":"Lucas, C. (2019). Point cloud hole filling. https:\/\/github.com\/Geodan\/fill-holes-pointcloud."},{"key":"1807_CR57","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., & Fan, Z., et\u00a0al. (2021). Conditional detr for fast training convergence. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 3651\u20133660).","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"1807_CR58","unstructured":"Mscoco. (2018). Mscoco detection leaderboard. http:\/\/cocodataset.org\/#detection-leaderboard."},{"issue":"1","key":"1807_CR59","first-page":"50","volume":"40","author":"R Nako","year":"2014","unstructured":"Nako, R., Wu, R., & Eimer, M. (2014). Rapid guidance of visual search by object categories. Journal of Experimental Psychology: Human Perception and Performance, 40(1), 50.","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"4","key":"1807_CR60","first-page":"1283","volume":"40","author":"R Nako","year":"2014","unstructured":"Nako, R., Wu, R., Smith, T. J., et al. (2014). Item and category-based attentional control during search for real-world objects: Can you find the pants among the pans? Journal of Experimental Psychology: Human Perception and Performance, 40(4), 1283.","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"key":"1807_CR61","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., & Shi, J., et\u00a0al. (2019). Libra r-cnn: Towards balanced learning for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp 821\u2013830).","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1807_CR62","unstructured":"Pinheiro, PO., Collobert, R., & Doll\u00e1r, P. (2015). Learning to segment object candidates. In NIPS"},{"key":"1807_CR63","doi-asserted-by":"crossref","unstructured":"Qi, CR., Litany, O., He, K., et\u00a0al. (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":"1807_CR64","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., & Jia, B., et\u00a0al. (2018). Learning human-object interactions by graph parsing neural networks. In CVPR","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"1807_CR65","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., & Girshick, R., et\u00a0al. (2016). You only look once: Unified, real-time object detection. In CVPR","DOI":"10.1109\/CVPR.2016.91"},{"key":"1807_CR66","doi-asserted-by":"crossref","unstructured":"Remez, T., Huang, J., & Brown, M. (2018). Learning to segment via cut-and-paste. In Proceedings of the European conference on computer vision (ECCV) (pp 37\u201352).","DOI":"10.1007\/978-3-030-01234-2_3"},{"key":"1807_CR67","unstructured":"Ren, S., He, K., & Girshick, R., et\u00a0al. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In NeurIPS"},{"key":"1807_CR68","doi-asserted-by":"crossref","unstructured":"Richtsfeld, A., M\u00f6rwald, T., & Prankl, J., et\u00a0al. (2012). Segmentation of unknown objects in indoor environments. In IROS","DOI":"10.1109\/IROS.2012.6385661"},{"key":"1807_CR69","doi-asserted-by":"crossref","unstructured":"Shao, D., Xiong, Y., & Zhao, Y., et\u00a0al. (2018). Find and focus: Retrieve and localize video events with natural language queries. In ECCV","DOI":"10.1007\/978-3-030-01240-3_13"},{"key":"1807_CR70","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., & Jiang, L., et\u00a0al. (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":"1807_CR71","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":"1807_CR72","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":"1807_CR73","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, SP., & Xiao, J. (2015). Sun rgb-d: A rgb-d scene understanding benchmark suite. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp 567\u2013576).","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"1807_CR74","doi-asserted-by":"crossref","unstructured":"Sun, J., Fang, HS., & Zhu, X., et\u00a0al. (2022). Correlation field for boosting 3d object detection in structured scenes. In Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v36i2.20128"},{"key":"1807_CR75","doi-asserted-by":"crossref","unstructured":"Sun, J., Li, Y., & Chai, L., et\u00a0al. (2022). Human trajectory prediction with momentary observation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 6467\u20136476)","DOI":"10.1109\/CVPR52688.2022.00636"},{"key":"1807_CR76","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., & Jiang, Y., et\u00a0al. (2021). Sparse r-cnn: End-to-end object detection with learnable proposals. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp 14454\u201314463).","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"1807_CR77","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., & Chen, H., et\u00a0al. (2019). Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9627\u20139636).","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"1","key":"1807_CR78","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1109\/TPAMI.2022.3145407","volume":"45","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Zhang, B., Chen, H., et al. (2022). Instance and panoptic segmentation using conditional convolutions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 669\u2013680.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1807_CR79","doi-asserted-by":"crossref","unstructured":"Tsai, YH., Shen, X., & Lin, Z., et\u00a0al. (2017). Deep image harmonization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3789\u20133797)","DOI":"10.1109\/CVPR.2017.299"},{"key":"1807_CR80","doi-asserted-by":"crossref","unstructured":"Wade, N., & Swanston, M. (2013). Visual perception: An introduction.","DOI":"10.4324\/9780203082263"},{"key":"1807_CR81","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., & Shen, C., et\u00a0al. (2020). Solo: Segmenting objects by locations. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16 (pp. 649\u2013665). Springer.","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"1807_CR82","unstructured":"Wang, W., Lai, Q., & Fu, H., et\u00a0al. (2019). Salient object detection in the deep learning era: An in-depth survey. arXiv preprint arXiv:1904.09146."},{"key":"1807_CR83","doi-asserted-by":"crossref","unstructured":"Wang, F., Wang, H., & Wei, C., et\u00a0al. (2022). Cp2: Copy-paste contrastive pretraining for semantic segmentation. arXiv preprint arXiv:2203.11709.","DOI":"10.1007\/978-3-031-20056-4_29"},{"issue":"1","key":"1807_CR84","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/TPAMI.2017.2662005","volume":"40","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., Yang, R., et al. (2017). Saliency-aware video object segmentation. TPAMI, 40(1), 20\u201333.","journal-title":"TPAMI"},{"key":"1807_CR85","first-page":"17721","volume":"33","author":"X Wang","year":"2020","unstructured":"Wang, X., Zhang, R., Kong, T., et al. (2020). Solov2: Dynamic and fast instance segmentation. Advances in Neural information processing systems, 33, 17721\u201317732.","journal-title":"Advances in Neural information processing systems"},{"key":"1807_CR86","doi-asserted-by":"crossref","unstructured":"Wu, R., McGee, B., & Echiverri, C., et\u00a0al. (2018). Prior knowledge of category size impacts visual search. Psychophysiology 55(8):e13075","DOI":"10.1111\/psyp.13075"},{"key":"1807_CR87","unstructured":"Xiao, A., Huang, J., & Guan, D., et\u00a0al. (2022). Polarmix: A general data augmentation technique for lidar point clouds. arXiv preprint arXiv:2208.00223"},{"key":"1807_CR88","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., & Guo, D., et\u00a0al. (2020). Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. In European Conference on Computer Vision (pp. 574\u2013591). Springer.","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"1807_CR89","doi-asserted-by":"crossref","unstructured":"Xie, Q., Lai, YK., & Wu, J., et\u00a0al. (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":"1807_CR90","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Liao, R., & Zhao, H., et\u00a0al. (2019). Upsnet: A unified panoptic segmentation network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 8818\u20138826).","DOI":"10.1109\/CVPR.2019.00902"},{"key":"1807_CR91","doi-asserted-by":"crossref","unstructured":"Xu, Z., Meng, A., & Shi, Z., et\u00a0al. (2021). Continuous copy-paste for one-stage multi-object tracking and segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 15323\u201315332).","DOI":"10.1109\/ICCV48922.2021.01504"},{"key":"1807_CR92","doi-asserted-by":"crossref","unstructured":"Xu, W., Wang, H., & Qi, F., et\u00a0al. (2019). Explicit shape encoding for real-time instance segmentation. arXiv:1908.04067.","DOI":"10.1109\/ICCV.2019.00527"},{"key":"1807_CR93","unstructured":"Yang, B., Liang, M., & Urtasun, R. (2018). Hdnet: Exploiting hd maps for 3d object detection. In Conference on Robot Learning (pp. 146\u2013155)"},{"key":"1807_CR94","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., & Urtasun, R. (2018). Pixor: Real-time 3d object detection from point clouds. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp. 7652\u20137660)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"1807_CR95","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, Y., Liang, Y., et\u00a0al. (2021). Tumorcp: A simple but effective object-level data augmentation for tumor segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp 579\u2013588). Springer.","DOI":"10.1007\/978-3-030-87193-2_55"},{"issue":"10","key":"1807_CR96","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":"1807_CR97","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":"1807_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Sun, B., & Yang, H., et\u00a0al. (2020). H3dnet: 3d object detection using hybrid geometric primitives. In European Conference on Computer Vision (pp. 311\u2013329). Springer.","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"1807_CR99","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":"1807_CR100","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850."},{"key":"1807_CR101","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., et al. (2022). Detecting twenty-thousand classes using image-level supervision. In I. X. Part (Ed.), Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings (pp. 350\u2013368). Springer."},{"key":"1807_CR102","doi-asserted-by":"crossref","unstructured":"Zhu, SC., & Mumford, D., et\u00a0al. (2007). A stochastic grammar of images. Foundations and Trends\u00ae in Computer Graphics and Vision","DOI":"10.1561\/0600000018"},{"key":"1807_CR103","unstructured":"Zhu, X., Su, W., & Lu, L., et\u00a0al. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01807-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01807-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01807-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T02:10:08Z","timestamp":1692411008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01807-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":103,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1807"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01807-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"18 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}