{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:24:07Z","timestamp":1748586247376,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333798"},{"type":"electronic","value":"9783031333804"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-33380-4_12","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T08:05:58Z","timestamp":1685088358000},"page":"153-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MIDFA: Memory-Based Instance Division and\u00a0Feature Aggregation Network for\u00a0Video Object Detection"],"prefix":"10.1007","author":[{"given":"Qiaochuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"12_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-030-01258-8_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Bertasius","year":"2018","unstructured":"Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatiotemporal sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 342\u2013357. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_21"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Optimizing video object detection via a scale-time lattice. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7814\u20137823 (2018)","DOI":"10.1109\/CVPR.2018.00815"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10337\u201310346 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Deng, H., et al.: Object guided external memory network for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6678\u20136687 (2019)","DOI":"10.1109\/ICCV.2019.00678"},{"key":"12_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7023\u20137032 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Gong, T., et al.: Temporal ROI align for video object recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1442\u20131450 (2021)","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Class-aware feature aggregation network for video object detection. IEEE Trans. Circuits Syst. Video Technol. 32, 8165\u20138178 (2021)","DOI":"10.1109\/TCSVT.2021.3094533"},{"issue":"10","key":"12_CR9","doi-asserted-by":"publisher","first-page":"2927","DOI":"10.1007\/s11263-021-01507-2","volume":"129","author":"L Han","year":"2021","unstructured":"Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Context and structure mining network for video object detection. Int. J. Comput. Vision 129(10), 2927\u20132946 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR10","unstructured":"Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"He, F., Gao, N., Li, Q., Du, S., Zhao, X., Huang, K.: Temporal context enhanced feature aggregation for video object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10941\u201310948 (2020)","DOI":"10.1609\/aaai.v34i07.6727"},{"key":"12_CR12","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":"12_CR13","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"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Lin, L.: Dual semantic fusion network for video object detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1855\u20131863 (2020)","DOI":"10.1145\/3394171.3413583"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Luo, H., Xie, W., Wang, X., Zeng, W.: Detect or track: towards cost-effective video object detection\/tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8803\u20138810 (2019)","DOI":"10.1609\/aaai.v33i01.33018803"},{"key":"12_CR16","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"3","key":"12_CR17","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":"12_CR18","doi-asserted-by":"crossref","unstructured":"Shvets, M., Liu, W., Berg, A.C.: Leveraging long-range temporal relationships between proposals for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9756\u20139764 (2019)","DOI":"10.1109\/ICCV.2019.00985"},{"key":"12_CR19","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2620\u20132627 (2021)","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9217\u20139225 (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137218 (2018)","DOI":"10.1109\/CVPR.2018.00753"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"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"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33380-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:55:10Z","timestamp":1710359710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33380-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333798","9783031333804"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33380-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","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":"813","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":"143","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":"18% - 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":"3.5","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":"10","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)"}}]}}