{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:38:33Z","timestamp":1743043113687,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200588"},{"type":"electronic","value":"9783031200595"}],"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\/978-3-031-20059-5_15","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"254-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Linguistic Association Towards Efficient Text-Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-4082","authenticated-orcid":false,"given":"Sheng","family":"Fang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9587-498X","authenticated-orcid":false,"given":"Junbao","family":"Zhuo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4599-7399","authenticated-orcid":false,"given":"Xinzhe","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: Vivit: a video vision transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 6816\u20136826. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00676","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"15_CR2","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":"15_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 813\u2013824. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/bertasius21a.html"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535\u2013541 (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained text-video 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":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chen, W., Li, G., Zhang, X., Yu, H., Wang, S., Huang, Q.: Cascade cross-modal attention network for video actor and action segmentation from a sentence. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4053\u20134062 (2021)","DOI":"10.1145\/3474085.3475534"},{"key":"15_CR7","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"},{"issue":"12","key":"15_CR8","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TMM.2018.2832602","volume":"20","author":"J Dong","year":"2018","unstructured":"Dong, J., Li, X., Snoek, C.G.: Predicting visual features from text for image and video caption retrieval. IEEE Trans. Multimedia 20(12), 3377\u20133388 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9346\u20139355 (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"15_CR10","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4065\u20134080 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR11","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, 3\u20136 September 2018, p. 12. BMVA Press (2018). http:\/\/bmvc2018.org\/contents\/papers\/0344.pdf"},{"key":"15_CR12","unstructured":"Foteini, M., et al.: Iti-certh participation in trecvid 2016. In: TRECVID 2016 Workshop (2016)"},{"key":"15_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"15_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"15_CR15","unstructured":"Junbao, Z., et al.: Zero-shot video classification with appropriate web and task knowledge transfer. In: Proceedings of the 30th ACM International Conference on Multimedia (2022)"},{"key":"15_CR16","unstructured":"Le, D.D., et al.: Nii-hitachi-uit at trecvid 2016. In: TRECVID, vol. 25 (2016)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Lei, Jet 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":"15_CR18","doi-asserted-by":"crossref","unstructured":"Li, Q., Jin, S., Yan, J.: Mimicking very efficient network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6356\u20136364 (2017)","DOI":"10.1109\/CVPR.2017.776"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2vv++ fully deep learning for ad-hoc video search. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1786\u20131794 (2019)","DOI":"10.1145\/3343031.3350906"},{"issue":"12","key":"15_CR20","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935\u20132947 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR21","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=S1eYHoC5FX"},{"key":"15_CR22","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":"15_CR23","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. In: 30th British Machine Vision Conference 2019, BMVC 2019, Cardiff, UK, 9\u201312 September 2019, p. 279. BMVA Press (2019). https:\/\/bmvc2019.org\/wp-content\/uploads\/papers\/0363-paper.pdf"},{"key":"15_CR24","unstructured":"Luo, H., et al.: Clip4clip: an empirical study of CLIP for end to end video clip retrieval. CoRR abs\/2104.08860 (2021). https:\/\/arxiv.org\/abs\/2104.08860"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Markatopoulou, F., Galanopoulos, D., Mezaris, V., Patras, I.: Query and keyframe representations for ad-hoc video search. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, pp. 407\u2013411 (2017)","DOI":"10.1145\/3078971.3079041"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9826\u20139836 (2021)","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"15_CR27","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 (2018)"},{"key":"15_CR28","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":"15_CR29","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal text-video retrieval. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp. 19\u201327 (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"15_CR30","unstructured":"Nguyen, P.A., et al.: Vireo@ trecvid 2017: video-to-text, ad-hoc video search, and video hyperlinking. In: TRECVID (2017)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3967\u20133976 (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"15_CR32","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=EqoXe2zmhrh"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Towards more explainability: concept knowledge mining network for event recognition. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 3857\u20133865 (2020)","DOI":"10.1145\/3394171.3413954"},{"key":"15_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923","author":"Z Qi","year":"2021","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Self-regulated learning for egocentric video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3059923","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Zhang, W., Huang, Q.: Modeling temporal concept receptive field dynamically for untrimmed video analysis. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 3798\u20133806 (2020)","DOI":"10.1145\/3394171.3413618"},{"key":"15_CR36","unstructured":"Sheng, F., et al.: Concept propagation via attentional knowledge graph reasoning for video-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia (2022)"},{"key":"15_CR37","unstructured":"Snoek, C.G., Li, X., Xu, C., Koelma, D.C.: University of amsterdam and renmin university at trecvid 2017: searching video, detecting events and describing video. In: TRECVID (2017)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"15_CR39","unstructured":"Ueki, K., Hirakawa, K., Kikuchi, K., Ogawa, T., Kobayashi, T.: Waseda_meisei at trecvid 2017: ad-hoc video search. In: TRECVID (2017)"},{"key":"15_CR40","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"15_CR41","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2021","unstructured":"Wang, L., Yoon, K.J.: Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3048\u20133068 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR42","doi-asserted-by":"publisher","unstructured":"Wang, T., Zhang, R., Lu, Z., Zheng, F., Cheng, R., Luo, P.: End-to-end dense video captioning with parallel decoding. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 6827\u20136837. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00677","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"15_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":"15_CR44","doi-asserted-by":"crossref","unstructured":"Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 450\u2013459 (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"15_CR45","doi-asserted-by":"publisher","unstructured":"Yang, X., Dong, J., Cao, Y., Wang, X., Wang, M., Chua, T.: Tree-augmented cross-modal encoding for complex-query video retrieval. In: Huang, J., et al. (eds.) Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, SIGIR 2020, Virtual Event, China, 25\u201330 July 2020, pp. 1339\u20131348. ACM (2020). https:\/\/doi.org\/10.1145\/3397271.3401151","DOI":"10.1145\/3397271.3401151"}],"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\/978-3-031-20059-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:07:09Z","timestamp":1666973229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 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)"}}]}}