{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:43:14Z","timestamp":1783039394554,"version":"3.54.6"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197802","type":"print"},{"value":"9783031197819","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19781-9_19","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"319-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":127,"title":["TS2-Net: Token Shift and\u00a0Selection Transformer for\u00a0Text-Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2119-0881","authenticated-orcid":false,"given":"Yuqi","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luhui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9342-1837","authenticated-orcid":false,"given":"Shengming","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6486-6020","authenticated-orcid":false,"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Abernethy, J., Lee, C., Tewari, A.: Perturbation techniques in online learning and optimization. Perturbations, Optimization, and Statistics, p. 223 (2016)","DOI":"10.7551\/mitpress\/10761.003.0009"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Anne Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE international conference on computer vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: A joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"19_CR5","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding. arXiv preprint arXiv:2102.05095 (2021)"},{"key":"19_CR6","unstructured":"Berthet, Q., Blondel, M., Teboul, O., Cuturi, M., Vert, J.P., Bach, F.: Learning with differentiable pertubed optimizers. Advances in neural information processing systems, pp. 9508\u20139519 (2020)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Bogolin, S.V., Croitoru, I., Jin, H., Liu, Y., Albanie, S.: Cross modal retrieval with querybank normalisation. arXiv preprint arXiv:2112.12777 (2021)","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"19_CR8","unstructured":"Bulat, A., Perez Rua, J.M., Sudhakaran, S., Martinez, B., Tzimiropoulos, G.: Space-time mixing attention for video transformer. In: Advances in Neural Information Processing Systems (2021)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"19_CR10","unstructured":"Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pp. 190\u2013200 (2011)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10638\u201310647 (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"19_CR12","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., Shen, D.: Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290 (2021)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Cordonnier, J.B., Mahendran, A., Dosovitskiy, A., Weissenborn, D., Uszkoreit, J., Unterthiner, T.: Differentiable patch selection for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2351\u20132360 (2021)","DOI":"10.1109\/CVPR46437.2021.00238"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Croitoru, I., et al.: Teachtext: Crossmodal generalized distillation for text-video retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11583\u201311593 (2021)","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9346\u20139355 (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"19_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Dzabraev, M., Kalashnikov, M., Komkov, S., Petiushko, A.: Mdmmt: Multidomain multimodal transformer for video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133363 (2021)","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Victor Escorcia, B.G., Niebles, J.C.: Activitynet: A large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"19_CR19","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: European Conference on Computer Vision, pp. 214\u2013229 (2020)","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"19_CR22","unstructured":"Gao, Z., Liu, J., Chen, S., Chang, D., Zhang, H., Yuan, J.: Clip2tv: An empirical study on transformer-based methods for video-text retrieval. arXiv preprint arXiv:2111.05610 (2021)"},{"key":"19_CR23","unstructured":"Goyal, P., et al.: Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"19_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd international Conferance for Learning Representations, San (2014)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE international conference on computer vision, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: Clipbert for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-vl: A universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11336\u201311344. No. 07 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., Liu, J.: Hero: Hierarchical encoder for video+ language omni-representation pre-training. arXiv preprint arXiv:2005.00200 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: Hit: Hierarchical transformer with momentum contrast for video-text retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11915\u201311925 (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"19_CR31","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487 (2019)"},{"key":"19_CR32","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)"},{"key":"19_CR33","unstructured":"Luo, H., et al.: Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: Clip4clip: An empirical study of clip for end to end video clip retrieval. arXiv preprint arXiv:2104.08860 (2021)","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"19_CR36","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 (2020)"},{"key":"19_CR37","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. pp. 8748\u20138763 (2021)"},{"key":"19_CR38","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog, p. 9 (2019)"},{"key":"19_CR39","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems (2021)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., et al.: Movie description. International Journal of Computer Vision, pp. 94\u2013120 (2017)","DOI":"10.1007\/s11263-016-0987-1"},{"key":"19_CR41","unstructured":"Su, W., et al.: Vl-bert: Pre-training of generic visual-linguistic representations. ICLR (2020)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, X., Li, H., Wu, Z., Jiang, Y.G.: Efficient video transformers with spatial-temporal token selection. arXiv preprint arXiv:2111.11591 (2021)","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2vlad: global-local sequence alignment for text-video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5079\u20135088 (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: Vatex: A large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: A large video description dataset for bridging video and language. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Yang, J., Bisk, Y., Gao, J.: Taco: Token-aware cascade contrastive learning for video-text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11562\u201311572 (2021)","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 471\u2013487 (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, B., Hu, H., Sha, F.: Cross-modal and hierarchical modeling of video and text. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 374\u2013390 (2018)","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 917\u2013925 (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and vqa. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19781-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:37:57Z","timestamp":1710261477000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19781-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197802","9783031197819"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19781-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}