{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:26:19Z","timestamp":1791303979494,"version":"4.1.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585167","type":"print"},{"value":"9783030585174","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\/978-3-030-58517-4_2","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T19:03:11Z","timestamp":1602270191000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Learning Where to Focus for Efficient Video Object Detection"],"prefix":"10.1007","author":[{"given":"Zhengkai","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ceyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,10]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Optimizing video object detection via a scale-time lattice. In: CVPR, pp. 7814\u20137823 (2018)","DOI":"10.1109\/CVPR.2018.00815"},{"key":"2_CR2","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NeurPIS, pp. 379\u2013387 (2016)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: CVPR, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Deng, H., et al.: Object guided external memory network for video object detection. In: ICCV, pp. 6678\u20136687 (2019)","DOI":"10.1109\/ICCV.2019.00678"},{"key":"2_CR5","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, pp. 248\u201325 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: ICCV, pp. 7023\u20137032 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: ICCV, pp. 3038\u20133046 (2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: CVPR, pp. 6639\u20136648 (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1007\/978-3-030-01246-5_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Gao","year":"2018","unstructured":"Gao, P., et al.: Question-guided hybrid convolution for visual question answering. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 485\u2013501. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_29"},{"issue":"11","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"2_CR13","unstructured":"Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR17","unstructured":"Hetang, C., Qin, H., Liu, S., Yan, J.: Impression network for video object detection. arXiv preprint arXiv:1712.05896 (2017)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Gao, P., Guo, C., Zhang, Q., Xiang, S., Pan, C.: Video object detection with locally-weighted deformable neighbors. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"2_CR19","unstructured":"Jiang, Z., et al.: Learning motion priors for efficient video object detection. arXiv preprint arXiv:1911.05253 (2019)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: CVPR, pp. 727\u2013735 (2017)","DOI":"10.1109\/CVPR.2017.101"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Kang, K., Ouyang, W., Li, H., Wang, X.: Object detection from video tubelets with convolutional neural networks. In: CVPR, pp. 817\u2013825 (2016)","DOI":"10.1109\/CVPR.2016.95"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, J., Zeng, A., Wang, X.: Differentiable kernel evolution. In: CVPR, pp. 1834\u20131843 (2019)","DOI":"10.1109\/ICCV.2019.00192"},{"key":"2_CR26","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: NeurPIS, pp. 2204\u20132212 (2014)"},{"key":"2_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurPIS, pp. 91\u201399 (2015)"},{"issue":"3","key":"2_CR28","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. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR29","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Shvets, M., Liu, W., Berg, A.C.: Leveraging long-range temporal relationships between proposals for video object detection. In: ICCV, pp. 9756\u20139764 (2019)","DOI":"10.1109\/ICCV.2019.00985"},{"key":"2_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurPIS, pp. 568\u2013576 (2014)"},{"issue":"2","key":"2_CR33","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154\u2013171 (2013). https:\/\/doi.org\/10.1007\/s11263-013-0620-5","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurPIS, pp. 5998\u20136008 (2017)"},{"key":"2_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-3-030-01261-8_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Wang","year":"2018","unstructured":"Wang, S., Zhou, Y., Yan, J., Deng, Z.: Fully motion-aware network for video object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 557\u2013573. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_33"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: ICCV, pp. 9217\u20139225 (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"2_CR38","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":"2_CR39","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, M., Song, G., Zhou, H., Liu, Y.: Discriminability distillation in group representation learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58607-2_1"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, J., Liu, Z., Liu, Y., Wang, X.: Rotate-and-render: unsupervised photorealistic face rotation from single-view images. In: CVPR, pp. 5911\u20135920 (2020)","DOI":"10.1109\/CVPR42600.2020.00595"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: CVPR, pp. 7210\u20137218 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: ICCV, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: CVPR, pp. 2349\u20132358 (2017)","DOI":"10.1109\/CVPR.2017.441"}],"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\/978-3-030-58517-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:06:26Z","timestamp":1728432386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58517-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585167","9783030585174"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58517-4_2","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":"10 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}