{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:43:17Z","timestamp":1743039797245,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"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_18","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"220-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Memory Feature Aggregation for\u00a0Video Object Detection"],"prefix":"10.1007","author":[{"given":"Diwei","family":"Fan","sequence":"first","affiliation":[]},{"given":"Huicheng","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Jisheng","family":"Dang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"18_CR2","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: IEEE International Conference on Computer Vision, pp. 7022\u20137031 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Gong, T., et al.: Temporal ROI align for video object recognition. In: AAAI Conference on Artificial Intelligence, pp. 1442\u20131450 (2021)","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Han, L., Yin, Z.: Global memory and local continuity for video object detection. IEEE Trans. Multimed. (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3164253","DOI":"10.1109\/TMM.2022.3164253"},{"key":"18_CR7","unstructured":"Han, W., et al.: Seq-NMS for video object detection. arXiv:1602.08465 (2016)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"He, F., Gao, N., Jia, J., Zhao, X., Huang, K.: QueryProp: object query propagation for high-performance video object detection. In: AAAI Conference on Artificial Intelligence, pp. 834\u2013842 (2022)","DOI":"10.1609\/aaai.v36i1.19965"},{"key":"18_CR9","doi-asserted-by":"publisher","first-page":"108587","DOI":"10.1016\/j.patcog.2022.108587","volume":"127","author":"F He","year":"2022","unstructured":"He, F., Li, Q., Zhao, X., Huang, K.: Temporal-adaptive sparse feature aggregation for video object detection. Pattern Recogn. 127, 108587 (2022)","journal-title":"Pattern Recogn."},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","volume":"45","author":"L He","year":"2023","unstructured":"He, L., et al.: TransVOD: end-to-end video object detection with spatial-temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45, 7853\u20137869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Hashmi, K. A., Pagani, A., Stricker, D., Afzal, M. Z.: BoxMask: revisiting bounding box supervision for video object detection. In: IEEE Winter Conference on Applications of Computer Vision, pp. 2029\u20132039 (2023)","DOI":"10.1109\/WACV56688.2023.00207"},{"key":"18_CR15","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2018","unstructured":"Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28, 2896\u20132907 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"18_CR16","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318\u2013327 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR17","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":"18_CR18","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"18_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2014)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR20","unstructured":"Shaoqing Ren, Kaiming He, R.B.G., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Shvets, M., Liu, W., Berg, A.C.: Leveraging long-range temporal relationships between proposals for video object detection. In: IEEE International Conference on Computer Vision, pp. 9755\u20139763 (2019)","DOI":"10.1109\/ICCV.2019.00985"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Sun, G., Hua, Y., Hu, G., Robertson, N.M.: MAMBA: multi-level aggregation via memory bank for video object detection. In: AAAI Conference on Artificial Intelligence, pp. 2620\u20132627 (2021)","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"18_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"18_CR24","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":"18_CR25","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: IEEE International Conference on Computer Vision, pp. 9216\u20139224 (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"18_CR26","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":"18_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137218 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: IEEE International Conference on Computer Vision, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4141\u20134150 (2017)","DOI":"10.1109\/CVPR.2017.441"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:09:47Z","timestamp":1703531387000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_18","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)"}}]}}