{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T01:26:48Z","timestamp":1768267608040,"version":"3.49.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030678319","type":"print"},{"value":"9783030678326","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67832-6_7","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T17:44:48Z","timestamp":1611337488000},"page":"75-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Frame Aggregation and Multi-modal Fusion Framework for Video-Based Person Recognition"],"prefix":"10.1007","author":[{"given":"Fangtao","family":"Li","sequence":"first","affiliation":[]},{"given":"Wenzhe","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zihe","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chenghao","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"issue":"4","key":"7_CR2","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"7_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR6","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database forstudying face recognition in unconstrained environments (2008)"},{"key":"7_CR7","unstructured":"Li, C., et al.: Deep speaker: an end-to-end neural speaker embedding system. arXiv preprint arXiv:1705.02304 650 (2017)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Lin, R., Xiao, J., Fan, J.: NeXtVLAD: an efficient neural network to aggregate frame-level features for large-scale video classification. In: ECCV, p. 0 (2018)","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"7_CR9","unstructured":"Liu, Y., et al.: iQIYI-VID: a large dataset for multi-modal person identification. arXiv preprint arXiv:1811.07548 (2018)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: iQIYI celebrity video identification challenge. In: ACM MM, pp. 2516\u20132520 (2019)","DOI":"10.1145\/3343031.3356081"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A.B., Morency, L.P.: Efficient low-rank multimodal fusion with modality-specific factors. In: ACL, pp. 2247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Mai, S., Hu, H., Xing, S.: Modality to modality translation: an adversarial representation learning and graph fusion network for multimodal fusion. In: AAAI, pp. 164\u2013172. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Song, G., Leng, B., Liu, Y., Hetang, C., Cai, S.: Region-based quality estimation network for large-scale person re-identification. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12305"},{"key":"7_CR14","unstructured":"Tang, P., Wang, X., Shi, B., Bai, X., Liu, W., Tu, Z.: Deep FisherNet for object classification. arXiv preprint arXiv:1608.00182 (2016)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: ACL, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Whitelam, C., et al.: IARPA Janus benchmark-B face dataset. In: CVPR, pp. 90\u201398 (2017)","DOI":"10.1109\/CVPRW.2017.87"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Xuan, H., Zhang, Z., Chen, S., Yang, J., Yan, Y.: Cross-modal attention network for temporal inconsistent audio-visual event localization. In: AAAI, pp. 279\u2013286. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"7_CR19","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: ICML, pp. 7354\u20137363 (2019)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: CVPR, pp. 2138\u20132147 (2019)","DOI":"10.1109\/CVPR.2019.00224"},{"key":"7_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-20890-5_3","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Y Zhong","year":"2019","unstructured":"Zhong, Y., Arandjelovi\u0107, R., Zisserman, A.: GhostVLAD for set-based face recognition. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11362, pp. 35\u201350. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20890-5_3"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67832-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T22:31:13Z","timestamp":1670884273000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67832-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678319","9783030678326"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67832-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","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":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","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":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","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":"73","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":"35% - 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":"2,63","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":"2,5","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)"}}]}}