{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:10:21Z","timestamp":1742987421306,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"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\/978-3-031-27077-2_7","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"82-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Spatio-Temporal Identity Verification Method for\u00a0Person-Action Instance Search in\u00a0Movies"],"prefix":"10.1007","author":[{"given":"Yanrui","family":"Niu","sequence":"first","affiliation":[]},{"given":"Jingyao","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Baojin","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"unstructured":"Awad, G., et al.: TRECVID 2018: Benchmarking video activity detection, video captioning and matching, video storytelling linking and video search. In: Proceedings of TRECVID 2018 (2018)","key":"7_CR1"},{"unstructured":"Awad, G., et al.: TRECVID 2017: evaluating ad-hoc and instance video search, events detection, video captioning, and hyperlinking. In: TREC Video Retrieval Evaluation (TRECVID) (2017)","key":"7_CR2"},{"unstructured":"Awad, G., et al.: TRECVID 2020: a comprehensive campaign for evaluating video retrieval tasks across multiple application domains. In: Proceedings of TRECVID 2020 (2020)","key":"7_CR3"},{"unstructured":"Awad, G., et al.: Evaluating multiple video understanding and retrieval tasks at TRECVID 2021. In: Proceedings of TRECVID 2021 (2021)","key":"7_CR4"},{"unstructured":"Awad, G., et al.: Trecvid 2019: an evaluation campaign to benchmark video activity detection, video captioning and matching, and video search retrieval. In: Proceedings of TRECVID 2019 (2019)","key":"7_CR5"},{"doi-asserted-by":"crossref","unstructured":"Awad, G., et al.: TRECVID 2016: evaluating video search, video event detection, localization, and hyperlinking. In: TREC Video Retrieval Evaluation (TRECVID) (2016)","key":"7_CR6","DOI":"10.1145\/3078971.3079044"},{"doi-asserted-by":"publisher","unstructured":"Bojanowski, P., Bach, F., Laptev, I., Ponce, J., Schmid, C., Sivic, J.: Finding actors and actions in movies. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2280\u20132287 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.283","key":"7_CR7","DOI":"10.1109\/ICCV.2013.283"},{"doi-asserted-by":"publisher","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 381\u2013389 (2018). https:\/\/doi.org\/10.1109\/WACV.2018.00048","key":"7_CR8","DOI":"10.1109\/WACV.2018.00048"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1016\/j.neucom.2020.07.118","volume":"453","author":"L Chen","year":"2021","unstructured":"Chen, L., Yang, H., Xu, Q., Gao, Z.: Harmonious attention network for person re-identification via complementarity between groups and individuals. Neurocomputing 453, 766\u2013776 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2020.07.118","journal-title":"Neurocomputing"},{"doi-asserted-by":"publisher","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: Retinaface: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00525","key":"7_CR10","DOI":"10.1109\/CVPR42600.2020.00525"},{"doi-asserted-by":"publisher","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00482","key":"7_CR11","DOI":"10.1109\/CVPR.2019.00482"},{"doi-asserted-by":"publisher","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6047\u20136056 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00633","key":"7_CR12","DOI":"10.1109\/CVPR.2018.00633"},{"key":"7_CR13","doi-asserted-by":"publisher","first-page":"9265","DOI":"10.1109\/ACCESS.2018.2890560","volume":"7","author":"IU Haq","year":"2019","unstructured":"Haq, I.U., Muhammad, K., Ullah, A., Baik, S.W.: Deepstar: Detecting starring characters in movies. IEEE Access 7, 9265\u20139272 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2018.2890560","journal-title":"IEEE Access"},{"unstructured":"Jiang, L., et al.: Whu-nercms at trecvid 2019: Instance search task. In: Proceedings of TRECVID Workshop (2019). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv19.papers\/whu_nercms.pdf","key":"7_CR14"},{"key":"7_CR15","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neucom.2019.06.088","volume":"362","author":"W Jiang","year":"2019","unstructured":"Jiang, W., Wu, Y., Jing, C., Yu, T., Jia, Y.: Unsupervised deep quantization for object instance search. Neurocomputing 362, 60\u201371 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2019.06.088","journal-title":"Neurocomputing"},{"unstructured":"Klinkigt, M., et al.: Nii hitachi uit at trecvid 2019. In: Proceedings of TRECVID Workshop (2019). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv19.papers\/nii_hitachi_uit.pdf","key":"7_CR16"},{"doi-asserted-by":"publisher","unstructured":"Laptev, I., Perez, P.: Retrieving actions in movies. In: 2007 IEEE 11th International Conference on Computer Vision (ICCV), pp. 1\u20138 (2007). https:\/\/doi.org\/10.1109\/ICCV.2007.4409105","key":"7_CR17","DOI":"10.1109\/ICCV.2007.4409105"},{"unstructured":"Le, D.D., et al.: Nii_uit at trecvid 2020. In: Proceedings of TRECVID Workshop (2020). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv20.papers\/nii_uit.pdf","key":"7_CR18"},{"doi-asserted-by":"publisher","unstructured":"Li, Y.L., et al.: Transferable interactiveness knowledge for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3585\u20133594 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00370","key":"7_CR19","DOI":"10.1109\/CVPR.2019.00370"},{"doi-asserted-by":"publisher","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: PPDM: Parallel point detection and matching for real-time human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 482\u2013490 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00056","key":"7_CR20","DOI":"10.1109\/CVPR42600.2020.00056"},{"issue":"1","key":"7_CR21","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TMM.2015.2500734","volume":"18","author":"J Meng","year":"2016","unstructured":"Meng, J., Yuan, J., Yang, J., Wang, G., Tan, Y.P.: Object instance search in videos via spatio-temporal trajectory discovery. IEEE Trans. Multimedia 18(1), 116\u2013127 (2016). https:\/\/doi.org\/10.1109\/TMM.2015.2500734","journal-title":"IEEE Trans. Multimedia"},{"unstructured":"Peng, Y., et al.: PKU-ICST at TRECVID 2019: Instance search task. In: Proceedings of TRECVID Workshop (2019). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv19.papers\/pku-icst.pdf","key":"7_CR22"},{"unstructured":"Peng, Y., Ye, Z., Zhang, J., Sun, H.: PKU WICT at TRECVID 2020: Instance search task. In: Proceedings of TRECVID Workshop (2020). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv20.papers\/pku-wict.pdf","key":"7_CR23"},{"doi-asserted-by":"publisher","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.C.: Learning human-object interactions by graph parsing neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 401\u2013417 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_25","key":"7_CR24","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"7_CR25","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-981-15-7345-3_10","volume-title":"Inventive Communication and Computational Technologies","author":"N Kumar","year":"2021","unstructured":"Kumar, N., Du, V., Doja, M.N., Shambharkar, P., Nimesh, U.K.: Automatic Face Recognition and Finding Occurrence of Actors in Movies. In: Ranganathan, G., Chen, J., Rocha, \u00c1lvaro. (eds.) Inventive Communication and Computational Technologies. LNNS, vol. 145, pp. 115\u2013129. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-15-7345-3_10"},{"doi-asserted-by":"publisher","unstructured":"Stoian, A., Ferecatu, M., Benois-Pineau, J., Crucianu, M.: Fast action localization in large-scale video archives. In: IEEE Trans. Cir. and Sys. for Video Technol. 26(10), 1917\u20131930 (2016). https:\/\/doi.org\/10.1109\/TCSVT.2015.2475835","key":"7_CR26","DOI":"10.1109\/TCSVT.2015.2475835"},{"key":"7_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-58555-6_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Tang","year":"2020","unstructured":"Tang, J., Xia, J., Mu, X., Pang, B., Lu, C.: Asynchronous Interaction Aggregation for Action Detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 71\u201387. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_5"},{"doi-asserted-by":"publisher","unstructured":"Ulutan, O., Rallapalli, S., Srivatsa, M., Torres, C., Manjunath, B.S.: Actor conditioned attention maps for video action detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 527\u2013536 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093617","key":"7_CR28","DOI":"10.1109\/WACV45572.2020.9093617"},{"doi-asserted-by":"publisher","unstructured":"Wang, X., Liu, W., Chen, J., Wang, X., Yan, C., Mei, T.: Listen, look, and find the one: robust person search with multimodality index. ACM Trans. Multimedia Comput. Commun. Appl. 16(2) (2020). https:\/\/doi.org\/10.1145\/3380549","key":"7_CR29","DOI":"10.1145\/3380549"},{"doi-asserted-by":"publisher","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284\u2013293 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00037","key":"7_CR30","DOI":"10.1109\/CVPR.2019.00037"},{"key":"7_CR31","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1109\/TMM.2020.3001522","volume":"23","author":"F Yang","year":"2021","unstructured":"Yang, F., Yan, K., Lu, S., Jia, H., Xie, D., Yu, Z., Guo, X., Huang, F., Gao, W.: Part-aware progressive unsupervised domain adaptation for person re-identification. IEEE Trans. Multimedia 23, 1681\u20131695 (2021). https:\/\/doi.org\/10.1109\/TMM.2020.3001522","journal-title":"IEEE Trans. Multimedia"},{"unstructured":"Yang, J., Kang\u2019an Chen, Y.N., Fan, X., Liang, C.: WHU-NERCMS at TRECVID 2020: Instance search task. In: Proceedings of TRECVID Workshop (2020). https:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv20.papers\/whu_nercms.pdf","key":"7_CR32"},{"doi-asserted-by":"publisher","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: A face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5525\u20135533 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.596","key":"7_CR33","DOI":"10.1109\/CVPR.2016.596"},{"doi-asserted-by":"publisher","unstructured":"Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2403\u20132412 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00255","key":"7_CR34","DOI":"10.1109\/CVPR.2018.00255"},{"key":"7_CR35","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.neucom.2020.05.094","volume":"411","author":"W Zhang","year":"2020","unstructured":"Zhang, W., Wei, Z., Huang, L., Xie, K., Qin, Q.: Adaptive attention-aware network for unsupervised person re-identification. Neurocomputing 411, 20\u201331 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.05.094","journal-title":"Neurocomputing"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T04:33:28Z","timestamp":1729139608000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_7","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":"29 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","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":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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","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":"4","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)"}}]}}