{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:51:46Z","timestamp":1777567906336,"version":"3.51.4"},"publisher-location":"Cham","reference-count":95,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263156","type":"print"},{"value":"9783031263163","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_23","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"379-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Is an\u00a0Object-Centric Video Representation Beneficial for\u00a0Transfer?"],"prefix":"10.1007","author":[{"given":"Chuhan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankush","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1037\/0033-295X.99.4.605","volume":"99","author":"ES Spelke","year":"1992","unstructured":"Spelke, E.S., Breinlinger, K., Macomber, J., Jacobson, K.: Origins of knowledge. Psychol. Rev. 99, 605 (1992)","journal-title":"Psychol. Rev."},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1126\/science.1192788","volume":"331","author":"JB Tenenbaum","year":"2011","unstructured":"Tenenbaum, J.B., Kemp, C., Griffiths, T.L., Goodman, N.D.: How to grow a mind: statistics, structure, and abstraction. Science 331, 1279\u20131285 (2011)","journal-title":"Science"},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1111\/j.0956-7976.2005.00796.x","volume":"16","author":"K Grill-Spector","year":"2005","unstructured":"Grill-Spector, K., Kanwisher, N.: Visual recognition: as soon as you know it is there, you know what it is. Psychol. Sci. 16, 152\u2013160 (2005)","journal-title":"Psychol. Sci."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Herzig, R., et al.: Object-region video transformers. arXiv preprint arXiv:2110.06915 (2021)","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"23_CR5","unstructured":"Radevski, G., Moens, M.F., Tuytelaars, T.: Revisiting spatio-temporal layouts for compositional action recognition. In: Proceedings of BMVC (2021)"},{"key":"23_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tokmakov, P., Hebert, M., Schmid, C.: A structured model for action detection. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.01021"},{"key":"23_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Feng, J., Kalantidis, Y.: Graph-based global reasoning networks. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00052"},{"key":"23_CR10","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: NeurIPS (2020)"},{"key":"23_CR11","unstructured":"Battaglia, P., Pascanu, R., Lai, M., Jimenez Rezende, D., et al.: Interaction networks for learning about objects, relations and physics. In: NeurIPS (2016)"},{"key":"23_CR12","unstructured":"Kulkarni, T.D., Gupta, A., Ionescu, C., Borgeaud, S., Reynolds, M., Zisserman, A., Mnih, V.: Unsupervised learning of object keypoints for perception and control. In: NeurIPS (2019)"},{"key":"23_CR13","unstructured":"Dubey, R., Agrawal, P., Pathak, D., Griffiths, T.L., Efros, A.A.: Investigating human priors for playing video games. In: Proceedings of ICML (2018)"},{"key":"23_CR14","unstructured":"Gopnik, A., Meltzoff, A.N., Kuhl, P.K.: The scientist in the crib: what early learning tells us about the mind. William Morrow Paperbacks (2000)"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.tics.2018.02.004","volume":"22","author":"LB Smith","year":"2018","unstructured":"Smith, L.B., Jayaraman, S., Clerkin, E., Yu, C.: The developing infant creates a curriculum for statistical learning. Trends Cogn. Sci. 22, 324\u2013336 (2018)","journal-title":"Trends Cogn. Sci."},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"23_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Xiao, T., Herzig, R., Xu, H., Wang, X., Darrell, T.: Something-else: compositional action recognition with spatial-temporal interaction networks. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"23_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"23_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"23_CR23","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS (2014)"},{"key":"23_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"23_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58610-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.-B.: DRG: dual relation graph for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_41"},{"key":"23_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-01264-9_15","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Kato","year":"2018","unstructured":"Kato, K., Li, Y., Gupta, A.: Compositional learning for human object interaction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 247\u2013264. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_15"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Xu, B., Wong, Y., Li, J., Zhao, Q., Kankanhalli, M.S.: Learning to detect human-object interactions with knowledge. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00212"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"23_CR31","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: an approach for combining action understanding and object perception. In: Proceedings of CVPR (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"23_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-01261-8_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"F Baradel","year":"2018","unstructured":"Baradel, F., Neverova, N., Wolf, C., Mille, J., Mori, G.: Object level visual reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 106\u2013122. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_7"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Arnab, A., Sun, C., Schmid, C.: Unified graph structured models for video understanding. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"23_CR36","unstructured":"Yan, R., Xie, L., Shu, X., Tang, J.: Interactive fusion of multi-level features for compositional activity recognition. arXiv preprint arXiv:2012.05689 (2020)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., AlRegib, G., Graf, H.P.: Attend and interact: higher-order object interactions for video understanding. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00710"},{"key":"23_CR38","unstructured":"Kolesnikov, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: Proceedings of ICLR (2021)"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"23_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"23_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"key":"23_CR43","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: See, hear, and read: Deep aligned representations. arXiv preprint arXiv:1706.00932 (2017)"},{"key":"23_CR44","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T.: Devise: a deep visual-semantic embedding model. In: NeurIPS (2013)"},{"key":"23_CR45","unstructured":"Weston, J., Bengio, S., Usunier, N.: Wsabie: Scaling up to large vocabulary image annotation. In: Proceedings of IJCAI (2011)"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"23_CR48","unstructured":"Patrick, M., Campbell, D., Asano, Y., Misra, I., Metze, F., Feichtenhofer, C., Vedaldi, A., Henriques, J.F.: Keeping your eye on the ball: Trajectory attention in video transformers. In: NeurIPS (2021)"},{"key":"23_CR49","unstructured":"Alayrac, J.B., et al.: Self-supervised multimodal versatile networks. In: NeurIPS (2020)"},{"key":"23_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-030-01261-8_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Nagrani","year":"2018","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Learnable PINs: cross-modal embeddings for person identity. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 73\u201389. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_5"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"23_CR52","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2014","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2014). https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"23_CR54","unstructured":"Kristan, M., et al.: The ninth visual object tracking vot2021 challenge results. In: Proceedings of ICCV (2021)"},{"key":"23_CR55","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. In: IEEE PAMI (2019)"},{"key":"23_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58558-7_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Dave","year":"2020","unstructured":"Dave, A., Khurana, T., Tokmakov, P., Schmid, C., Ramanan, D.: TAO: a large-scale benchmark for tracking any object. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_26"},{"key":"23_CR57","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer, P., et al.: Motchallenge: a benchmark for single-camera multiple target tracking. IJCV. 129, 845\u2013881 (2021)","journal-title":"IJCV."},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"23_CR59","unstructured":"Xu, N., et al.: Youtube-VOS: A large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"Wang, W., Feiszli, M., Wang, H., Tran, D.: Unidentified video objects: a benchmark for dense, open-world segmentation. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"23_CR62","unstructured":"Girdhar, R., Ramanan, D.: CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning. In: ICLR (2020)"},{"key":"23_CR63","unstructured":"Yi, K., Gan, C., Li, Y., Kohli, P., Wu, J., Torralba, A., Tenenbaum, J.B.: Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019)"},{"key":"23_CR64","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Krishna, R., Chami, I., Bernstein, M., Fei-Fei, L.: Referring relationships. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00718"},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Saenko, K., et al.: Mid-level features improve recognition of interactive activities. Department of Electrical Engineering and Computer Science. University of California, Berkeley, Technical report (2012)","DOI":"10.21236\/ADA570728"},{"key":"23_CR68","unstructured":"Xu, H., Yang, L., Sclaroff, S., Saenko, K., Darrell, T.: Spatio-temporal action detection with multi-object interaction. arXiv preprint arXiv:2004.00180 (2020)"},{"key":"23_CR69","unstructured":"Battaglia, P., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Ye, Y., Singh, M., Gupta, A., Tulsiani, S.: Compositional video prediction. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.01045"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Liang, J., Jiang, L., Niebles, J.C., Hauptmann, A.G., Fei-Fei, L.: Peeking into the future: predicting future person activities and locations in videos. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00587"},{"key":"23_CR72","doi-asserted-by":"crossref","unstructured":"Wu, Y., Gao, R., Park, J., Chen, Q.: Future video synthesis with object motion prediction. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00558"},{"key":"23_CR73","unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. In: Proceedings of ICML (2019)"},{"key":"23_CR74","unstructured":"Henderson, P., Lampert, C.H.: Unsupervised object-centric video generation and decomposition in 3d. In: NeurIPS (2020)"},{"key":"23_CR75","doi-asserted-by":"crossref","unstructured":"Yang, C., Lamdouar, H., Lu, E., Zisserman, A., Xie, W.: Self-supervised video object segmentation by motion grouping. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"23_CR76","unstructured":"Burgess, C.P., et al.: Monet: Unsupervised scene decomposition and representation. arXiv preprint arXiv:1901.11390 (2019)"},{"key":"23_CR77","unstructured":"Engelcke, M., Kosiorek, A.R., Jones, O.P., Posner, I.: Genesis: Generative scene inference and sampling with object-centric latent representations. arXiv preprint arXiv:1907.13052 (2019)"},{"key":"23_CR78","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"23_CR79","unstructured":"Herzig, R., Raboh, M., Chechik, G., Berant, J., Globerson, A.: Mapping images to scene graphs with permutation-invariant structured prediction. In: NeurIPS (2018)"},{"key":"23_CR80","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: GauGAN: semantic image synthesis with spatially adaptive normalization. In: ACM SIGGRAPH 2019 Real-Time Live (2019)","DOI":"10.1145\/3306305.3332370"},{"key":"23_CR81","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Ojha, U., Lee, Y.J.: FineGAN: unsupervised hierarchical disentanglement for fine-grained object generation and discovery. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00665"},{"key":"23_CR82","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"23_CR83","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-58574-7_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Herzig","year":"2020","unstructured":"Herzig, R., Bar, A., Xu, H., Chechik, G., Darrell, T., Globerson, A.: Learning canonical representations for scene graph to image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 210\u2013227. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_13"},{"key":"23_CR84","unstructured":"Ye, Y., Gandhi, D., Gupta, A., Tulsiani, S.: Object-centric forward modeling for model predictive control. In: Proceedings of CoRL (2020)"},{"key":"23_CR85","doi-asserted-by":"crossref","unstructured":"Devin, C., Abbeel, P., Darrell, T., Levine, S.: Deep object-centric representations for generalizable robot learning. In: Proceedings of International Conference on Robotics and Automation (2018)","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"23_CR86","unstructured":"Bapst, V., et al.: Structured agents for physical construction. In: Proceedings of ICML (2019)"},{"key":"23_CR87","unstructured":"Anand, A., Racah, E., Ozair, S., Bengio, Y., C\u00f4t\u00e9, M.A., Hjelm, R.D.: Unsupervised state representation learning in Atari. In: NeurIPS (2019)"},{"key":"23_CR88","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"23_CR89","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of ICLR (2019)"},{"key":"23_CR90","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"23_CR91","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"23_CR92","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878 (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"23_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. arXiv preprint arXiv:2110.06864 (2021)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"23_CR94","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"23_CR95","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:29:09Z","timestamp":1677659349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":95,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}