{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:39:13Z","timestamp":1778081953271,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198328","type":"print"},{"value":"9783031198335","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19833-5_1","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Efficient One-Stage Video Object Detection by\u00a0Exploiting Temporal Consistency"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1901-9097","authenticated-orcid":false,"given":"Guanxiong","family":"Sun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5536-503X","authenticated-orcid":false,"given":"Yang","family":"Hua","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9448-9892","authenticated-orcid":false,"given":"Guosheng","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2461-8799","authenticated-orcid":false,"given":"Neil","family":"Robertson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yan, L., Cao, Z., Liu, D.: TF-blender: temporal feature blender for video object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"1_CR3","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NeurIPS (2016)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Dynamic head: unifying object detection heads with attentions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"1_CR5","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 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J.: Ota: optimal transport assignment for object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"1_CR7","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1_CR10","unstructured":"Han, W., et al.: SEQ-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)"},{"key":"1_CR11","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":"1_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, L., et al.: End-to-end video object detection with spatial-temporal transformers. In: ACMMM (2021)","DOI":"10.1145\/3474085.3475285"},{"key":"1_CR14","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)"},{"key":"1_CR15","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":"10","key":"1_CR16","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., et al.: T-CNN: Tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896\u20132907 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/978-3-030-01264-9_45","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Law","year":"2018","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 765\u2013781. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_45"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In: NeurIPS (2020)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"1_CR19","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 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1_CR20","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 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-58568-6_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Lu","year":"2020","unstructured":"Lu, X., Li, Q., Li, B., Yan, J.: MimicDet: bridging the gap between one-stage and two-stage object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 541\u2013557. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_32"},{"key":"1_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1_CR26","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"issue":"3","key":"1_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. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"1_CR29","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 (2019)","DOI":"10.1109\/ICCV.2019.00985"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Sun, G., Hua, Y., Hu, G., Robertson, N.: Mamba: multi-level aggregation via memory bank for video object detection. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. arXiv preprint arXiv:1904.01355 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1_CR32","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":"1_CR33","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"1_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1007\/978-3-030-58595-2_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Xu","year":"2020","unstructured":"Xu, Z., Hrustic, E., Vivet, D.: CenterNet heatmap propagation for real-time video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 220\u2013234. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_14"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: an IOU-aware dense object detector. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"1_CR36","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1_CR38","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., Kr\u00e4henb\u00fchl, P.: Bottom-up object detection by grouping extreme and center points. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Zhu, X., Wei, Y., Yuan, L.: Towards high performance video object detection for mobiles. arXiv preprint arXiv:1804.05830 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"1_CR41","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 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.441"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19833-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:27:53Z","timestamp":1673278073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}