{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:35:33Z","timestamp":1783427733813,"version":"3.54.6"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3463799","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T17:24:49Z","timestamp":1726853089000},"page":"11409-11421","source":"Crossref","is-referenced-by-count":17,"title":["CoVR-2: Automatic Data Construction for Composed Video Retrieval"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5795-0064","authenticated-orcid":false,"given":"Lucas","family":"Ventura","sequence":"first","affiliation":[{"name":"LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7258-571X","authenticated-orcid":false,"given":"Antoine","family":"Yang","sequence":"additional","affiliation":[{"name":"Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7239-3741","authenticated-orcid":false,"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria, Ecole normale supérieure, CNRS, PSL Research University, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8438-6152","authenticated-orcid":false,"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[{"name":"LIGM, École des Ponts, CNRS, Univ Gustave Eiffel, Champs-sur-Marne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref6","article-title":"CompoDiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref7","article-title":"Data roaming and early fusion for composed image retrieval","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Levy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref10","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref14","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"ref16","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref17","article-title":"A CLIP-hitchhiker\u2019s guide to long video retrieval","author":"Bain","year":"2022"},{"key":"ref18","first-page":"676","article-title":"Dialog-based interactive image retrieval","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref19","article-title":"ARTEMIS: Attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Delmas"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref22","article-title":"MagicLens: Self-supervised image retrieval with open-ended instructions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref23","article-title":"Training-free zero-shot composed image retrieval with local concept reranking","author":"Sun","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref25","article-title":"Vision-by-language for training-free compositional image retrieval","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karthik"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref27","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref29","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref31","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref32","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref33","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref34","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref40","article-title":"Long-form video-language pre-training with multimodal temporal contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01033"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref45","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref46","article-title":"CLIP2Video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref47","article-title":"CLIP2TV: An empirical study on transformer-based methods for video-text retrieval","author":"Gao","year":"2021"},{"key":"ref48","first-page":"16146","article-title":"BridgeFormer: Bridging video-text retrieval with multiple choice questions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ge"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref53","article-title":"CLIP-vip: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref55","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao"},{"key":"ref56","article-title":"LuminosoInsight\/wordfreq: v2.2","author":"Speer","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","article-title":"CurlingNet: Compositional learning between images and text for fashionIQ data","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. Workshop","author":"Yu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref64","article-title":"TRACE: Transform aggregate and compose visiolinguistic representations for image search with text feedback","author":"Jandial","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref66","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"},{"key":"ref67","article-title":"RTIC: Residual learning for text and image composition using graph convolutional network","author":"Shin","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref71","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref72","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10685001.pdf?arnumber=10685001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:56:59Z","timestamp":1732665419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10685001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":72,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3463799","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}