{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:50:23Z","timestamp":1742914223255,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985364"},{"type":"electronic","value":"9789819985371"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8537-1_12","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"146-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Relation-Guided Multi-stage Feature Aggregation Network for\u00a0Video Object Detection"],"prefix":"10.1007","author":[{"given":"Tingting","family":"Yao","sequence":"first","affiliation":[]},{"given":"Fuxiao","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Fuheng","family":"Mi","sequence":"additional","affiliation":[]},{"given":"Danmeng","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"issue":"10","key":"12_CR1","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., Li, H., Yan, J., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circ. Syst. Video Technol. 28(10), 2896\u20132907 (2017)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Xiong, B., Kalantidis, Y., Ghadiyaram, D., et al.: Less is More: learning highlight detection from video duration. In: CVPR, pp. 1\u201313 (2019)","DOI":"10.1109\/CVPR.2019.00135"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1137\u20131149 (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"12_CR4","unstructured":"Dai, J., Li, Y., He, K., et al.: R-FCN: object detection via region-based fully convolutional networks. arXiv preprint arXiv:1605.06409 (2016)"},{"issue":"10","key":"12_CR5","doi-asserted-by":"publisher","first-page":"2537","DOI":"10.1109\/TIFS.2019.2900907","volume":"14","author":"JT Zhou","year":"2019","unstructured":"Zhou, J.T., Du, J., Zhu, H., et al.: Anomalynet: an anomaly detection network for video surveillance. IEEE Trans. Inf. Forensics Secur. 14(10), 2537\u20132550 (2019)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Ghadiyaram, D., et al.: MesoNet: a compact facial video forgery detection network. In: IEEE International Workshop on Information Forensics and Security, pp. 1\u20137(2018)","DOI":"10.1109\/WIFS.2018.8630761"},{"issue":"7","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1007\/s11760-017-1093-8","volume":"11","author":"SS Sengar","year":"2017","unstructured":"Sengar, S.S., Mukhopadhyay, S.: Moving object detection based on frame difference and Background Cumulant. IEEE Trans. Image Video Process. 11(7), 1357\u20131364 (2017)","journal-title":"IEEE Trans. Image Video Process."},{"key":"12_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24673-2_3"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et al.: FCOS: fully convolutional one-stage object detection. In: ICCV, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., et al.: Flow-guided feature aggregation for video object detection. In: ICCV, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., et al.: Deep feature flow for video recognition. In: CVPR, pp. 2349\u20132358 (2017)","DOI":"10.1109\/CVPR.2017.441"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., et al.: Towards high performance video object detection. In: CVPR, pp. 7210\u20137218 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhou, Y., Yan, J., et al.: Fully motion-aware network for video object detection. In: ECCV, pp. 542\u2013557 (2018)","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., et al.: Sequence level semantics aggregation for video object detection. In: ICCV, pp. 9217\u20139225 (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Shvets, M., Liu, W., Berg, A.: Leveraging long-range temporal relationships between proposals for video object detection. In: ICCV, pp. 9756\u20139764 (2019)","DOI":"10.1109\/ICCV.2019.00985"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., et al.: Memory enhanced global-local aggregation for video object detection. In: CVPR, pp. 10337\u201310346 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yan, L., Cao, Z., et al.: TF-blender: temporal feature blender for video object detection. In: ICCV, pp. 8138\u20138147 (2021)","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"12_CR18","doi-asserted-by":"publisher","first-page":"172443","DOI":"10.1109\/ACCESS.2020.3025780","volume":"8","author":"D Su","year":"2020","unstructured":"Su, D., Wang, H., Jin, L., et al.: Local-global fusion network for video super-resolution. IEEE Access 8, 172443\u2013172456 (2020)","journal-title":"IEEE Access"},{"issue":"3","key":"12_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR20","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":"12_CR21","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatio temporal sampling networks. In: ECCV, pp. 331\u2013346 (2018)","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., et al.: Relation distillation networks for video object detection. In: ICCV, pp. 7023\u20137032 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Gong, T., Chen, K., Wang, X., et al.: Temporal ROI align for video object recognition. In: American Association for Artificial Intelligence (AAAI), vol. 35, no. 2, pp. 1442\u20131450 (2021)","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"12_CR24","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"},{"issue":"11","key":"12_CR25","doi-asserted-by":"publisher","first-page":"7809","DOI":"10.1109\/TCSVT.2022.3183646","volume":"32","author":"C Xu","year":"2022","unstructured":"Xu, C., Zhang, J., Wang, M., et al.: Multi-level spatial-temporal feature aggregation for video object detection. IEEE Trans. Circ. Syst. Video Technol. 32(11), 7809\u20137820 (2022)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"12_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108587","volume":"127","author":"F He","year":"2022","unstructured":"He, F., Li, Q., Zhao, X.: Temporal-adaptive sparse feature aggregation for video object detection. Pattern Recogn. 127, 108587 (2022)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8537-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:08:43Z","timestamp":1703531323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}