{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:48:56Z","timestamp":1785458936029,"version":"3.56.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","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\/978-3-031-20074-8_42","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"732-747","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection"],"prefix":"10.1007","author":[{"given":"Han","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanyan","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: HIFT: hierarchical feature transformer for aerial tracking. In: ICCV, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"42_CR2","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":"42_CR3","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":"42_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: CVPR, pp. 10337\u201310346 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"42_CR6","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"42_CR7","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":"42_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: ICCV, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"42_CR10","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":"42_CR11","doi-asserted-by":"crossref","unstructured":"Gong, T., et al.: Temporal ROI align for video object recognition. In: AAAI, pp. 1442\u20131450 (2021)","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Progressive sparse local attention for video object detection. In: ICCV, pp. 3909\u20133918 (2019)","DOI":"10.1109\/ICCV.2019.00401"},{"key":"42_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-030-58589-1_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Han","year":"2020","unstructured":"Han, M., Wang, Y., Chang, X., Qiao, Yu.: Mining inter-video proposal relations for video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 431\u2013446. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_26"},{"key":"42_CR14","unstructured":"Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"42_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58517-4_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Jiang","year":"2020","unstructured":"Jiang, Z., et al.: Learning where to focus for efficient video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_2"},{"issue":"10","key":"42_CR17","first-page":"2896","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. TCSVT 28(10), 2896\u20132907 (2017)","journal-title":"TCSVT"},{"key":"42_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"42_CR19","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, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"42_CR20","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"42_CR21","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":"42_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, vol. 28 (2015)"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"issue":"3","key":"42_CR24","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)","journal-title":"Int. J. Comput. Vision"},{"key":"42_CR25","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":"42_CR26","doi-asserted-by":"crossref","unstructured":"Stewart, R., Andriluka, M., Ng, A.Y.: End-to-end people detection in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2325\u20132333 (2016)","DOI":"10.1109\/CVPR.2016.255"},{"key":"42_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: CVPR, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"42_CR29","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":"42_CR30","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":"42_CR31","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":"42_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, Q., et al.: TransVOD: end-to-end video object detection with spatial-temporal transformers. arXiv preprint arXiv:2201.05047 (2022)","DOI":"10.1109\/TPAMI.2022.3223955"},{"issue":"21","key":"42_CR33","doi-asserted-by":"publisher","first-page":"7834","DOI":"10.3390\/app10217834","volume":"10","author":"H Zhu","year":"2020","unstructured":"Zhu, H., Wei, H., Li, B., Yuan, X., Kehtarnavaz, N.: A review of video object detection: datasets, metrics and methods. Appl. Sci. 10(21), 7834 (2020)","journal-title":"Appl. Sci."},{"key":"42_CR34","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DeTR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"42_CR35","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":"42_CR36","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 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T21:50:44Z","timestamp":1678571444000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_42","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":"12 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)"}}]}}