{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T04:50:31Z","timestamp":1783918231821,"version":"3.55.0"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58558-7_26","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"436-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":126,"title":["TAO: A Large-Scale Benchmark for Tracking Any Object"],"prefix":"10.1007","author":[{"given":"Achal","family":"Dave","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarasha","family":"Khurana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavel","family":"Tokmakov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deva","family":"Ramanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"26_CR2","unstructured":"Barriuso, A., Torralba, A.: Notes on image annotation. arXiv preprint arXiv:1210.3448 (2012)"},{"key":"26_CR3","unstructured":"Berclaz, J., Fleuret, F., Fua, P.: Robust people tracking with global trajectory optimization. In: CVPR (2006)"},{"issue":"9","key":"26_CR4","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","volume":"33","author":"J Berclaz","year":"2011","unstructured":"Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using k-shortest paths optimization. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1806\u20131819 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"26_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. J. Image Video Process. 2008, 1 (2008). https:\/\/doi.org\/10.1155\/2008\/246309","journal-title":"J. Image Video Process."},{"key":"26_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: ICIP (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Robust tracking-by-detection using a detector confidence particle filter. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459278"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., Shah, R.: Signature verification using a \u201csiamese\u201d time delay neural network. In: NIPS (1994)","DOI":"10.1142\/9789812797926_0003"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"26_CR13","unstructured":"Caelles, S., Pont-Tuset, J., Perazzi, F., Montes, A., Maninis, K.K., Van Gool, L.: The 2019 DAVIS challenge on VOS: unsupervised multi-object segmentation. arXiv preprint arXiv:1905.00737 (2019)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Chang, M.F., et al.: Argoverse: 3D tracking and forecasting with rich maps. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00895"},{"key":"26_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/978-3-030-01234-2_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Chen","year":"2018","unstructured":"Chen, B., Wang, D., Li, P., Wang, S., Lu, H.: Real-time \u2018actor-critic\u2019 tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 328\u2013345. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_20"},{"key":"26_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/978-3-642-15561-1_40","volume-title":"Computer Vision \u2013 ECCV 2010","author":"W Choi","year":"2010","unstructured":"Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 553\u2013567. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_40"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ATOM: accurate tracking by overlap maximization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"26_CR19","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Ess, A., Leibe, B., Schindler, K., Van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"26_CR23","unstructured":"Fisher, R., Santos-Victor, J., Crowley, J.: Context aware vision using image-based active recognition. EC\u2019s Information Society Technology\u2019s Programme Project IST2001-3754 (2001)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"26_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/978-3-319-46448-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"D Held","year":"2016","unstructured":"Held, D., Thrun, S., Savarese, S.: Learning to track at 100 FPS with deep regression networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 749\u2013765. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_45"},{"key":"26_CR30","unstructured":"Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. arXiv preprint arXiv:1810.11981 (2018)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, H., Fels, S., Little, J.J.: A linear programming approach for multiple object tracking. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383180"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.101"},{"issue":"9","key":"26_CR33","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s11263-019-01164-6","volume":"127","author":"A Khoreva","year":"2019","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for video object segmentation. Int. J. Comput. Vis. 127(9), 1175\u20131197 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01164-6","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"26_CR34","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., et al.: A novel performance evaluation methodology for single-target trackers. TPAMI 38(11), 2137\u20132155 (2016)","journal-title":"TPAMI"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Fenzi, M., Kuznetsova, A., Rosenhahn, B., Savarese, S.: Learning an image-based motion context for multiple people tracking. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.453"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"26_CR38","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":"26_CR39","doi-asserted-by":"publisher","unstructured":"Loko\u010d, J., Koval\u010d\u00edk, G., Sou\u010dek, T., Moravec, J., \u010cech, P.: A framework for effective known-item search in video. In: ACMM (2019). https:\/\/doi.org\/10.1145\/3343031.3351046","DOI":"10.1145\/3343031.3351046"},{"key":"26_CR40","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Milan, A., Rezatofighi, S.H., Dick, A., Reid, I., Schindler, K.: Online multi-target tracking using recurrent neural networks. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11194"},{"issue":"6","key":"26_CR42","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TPAMI.2013.242","volume":"36","author":"P Ochs","year":"2013","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187\u20131200 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR43","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995604"},{"key":"26_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-01219-9_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Ren","year":"2018","unstructured":"Ren, L., Lu, J., Wang, Z., Tian, Q., Zhou, J.: Collaborative deep reinforcement learning for multi-object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 605\u2013621. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_36"},{"key":"26_CR46","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Ristani, E., Tomasi, C.: Features for multi-target multi-camera tracking and re-identification. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00632"},{"issue":"3","key":"26_CR48","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"issue":"1\u20133","key":"26_CR49","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: LabelMe: a database and web-based tool for image annotation. Int. J. Comput. Vis. 77(1\u20133), 157\u2013173 (2008). https:\/\/doi.org\/10.1007\/s11263-007-0090-8","journal-title":"Int. J. Comput. Vis."},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Tappen, M.F.: Learning pedestrian dynamics from the real world. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459224"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Shang, X., Di, D., Xiao, J., Cao, Y., Yang, X., Chua, T.S.: Annotating objects and relations in user-generated videos. In: ICMR (2019)","DOI":"10.1145\/3323873.3325056"},{"key":"26_CR52","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":"26_CR53","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. arXiv preprint arXiv:1503.01817 (2015)","DOI":"10.1145\/2812802"},{"key":"26_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1007\/978-3-030-01219-9_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Valmadre","year":"2018","unstructured":"Valmadre, J., et al.: Long-term tracking in the wild: a benchmark. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 692\u2013707. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_41"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation. In: CPVR (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"26_CR57","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)","DOI":"10.5244\/C.31.116"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"26_CR59","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Learning unsupervised video object segmentation through visual attention. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00318"},{"key":"26_CR60","unstructured":"Wen, L., et al.: UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. arXiv preprint arXiv:1511.04136 (2015)"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"26_CR62","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"26_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-030-01237-3_30","volume-title":"Computer Vision \u2013 ECCV 2018","author":"F Xiao","year":"2018","unstructured":"Xiao, F., Lee, Y.J.: Video object detection with an aligned spatial-temporal memory. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 494\u2013510. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_30"},{"key":"26_CR64","unstructured":"Xu, N., et al.: YouTube-VOS: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"26_CR65","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"26_CR66","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: CVPR, June 2020","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"26_CR67","unstructured":"Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)"},{"key":"26_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, H., Torralba, A., Torresani, L., Yan, Z.: HACS: human action clips and segments dataset for recognition and temporal localization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00876"},{"key":"26_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"26_CR70","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"26_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-030-01240-3_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103\u2013119. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_7"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58558-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:55:09Z","timestamp":1730105709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}