{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:28:30Z","timestamp":1743085710897,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031560262"},{"type":"electronic","value":"9783031560279"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56027-9_22","type":"book-chapter","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T07:02:49Z","timestamp":1710831769000},"page":"356-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Tuning CLIP via\u00a0Explainability Map Propagation for\u00a0Boosting Image and\u00a0Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-6646","authenticated-orcid":false,"given":"Yoav","family":"Shalev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5578-8892","authenticated-orcid":false,"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,20]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA, October 2021, pp. 387\u2013396. IEEE Computer Society (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00045. https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV48922.2021.00045","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"22_CR2","unstructured":"Chen, D., Dolan, W.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, June 2011, pp. 190\u2013200. Association for Computational Linguistics (2011). https:\/\/aclanthology.org\/P11-1020"},{"issue":"12","key":"22_CR3","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.M.: Predicting visual features from text for image and video caption retrieval. IEEE Trans. Multimedia 20(12), 3377\u20133388 (2018). https:\/\/doi.org\/10.1109\/TMM.2018.2832602","journal-title":"IEEE Trans. Multimedia"},{"key":"22_CR4","doi-asserted-by":"publisher","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9338\u20139347 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00957","DOI":"10.1109\/CVPR.2019.00957"},{"key":"22_CR5","doi-asserted-by":"publisher","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021). https:\/\/doi.org\/10.23915\/distill.00030. https:\/\/distill.pub\/2021\/multimodal-neurons","DOI":"10.23915\/distill.00030"},{"key":"22_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR7","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs\/1405.0312 (2014). http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"22_CR8","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. In: Proceedings of the British Machine Vision Conference (BMVC), September 2019 (2019)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"22_CR10","doi-asserted-by":"publisher","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, ICMR 2018, pp. 19\u201327. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3206025.3206064","DOI":"10.1145\/3206025.3206064"},{"key":"22_CR11","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 (2020)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Portillo-Quintero, J.A., Carlos Ort\u00edz-Bayliss, J., Terashima-Mar\u00edn, H.: A straightforward framework for video retrieval using CLIP. In: Mexican Conference on Pattern Recognition (2021). https:\/\/api.semanticscholar.org\/CorpusID:232035662","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"22_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"22_CR15","unstructured":"Su, Y., et al.: Language models can see: plugging visual controls in text generation. arXiv preprint arXiv:2205.02655 (2022)"},{"key":"22_CR16","unstructured":"Tewel, Y., Shalev, Y., Nadler, R., Schwartz, I., Wolf, L.: Zero-shot video captioning with evolving pseudo-tokens. arXiv arXiv:2207.11100 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251018313"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Shalev, Y., Schwartz, I., Wolf, L.: ZeroCap: zero-shot image-to-text generation for visual-semantic arithmetic. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17897\u201317907 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244714558","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"22_CR18","doi-asserted-by":"publisher","unstructured":"Wang, J., Liu, Y., Wang, X.: Are gender-neutral queries really gender-neutral? Mitigating gender bias in image search. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic, November 2021, pp. 1995\u20132008. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.151. https:\/\/aclanthology.org\/2021.emnlp-main.151","DOI":"10.18653\/v1\/2021.emnlp-main.151"},{"key":"22_CR19","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":"22_CR20","unstructured":"Zabari, N., Hoshen, Y.: Semantic segmentation in-the-wild without seeing any segmentation examples. arXiv preprint arXiv:2112.03185 (2021)"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56027-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T07:10:48Z","timestamp":1710832248000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56027-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560262","9783031560279"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56027-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"578","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":"110","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":"69","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":"19% - 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)"}},{"value":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}