{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:04Z","timestamp":1777865524854,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01138","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12242-12252","source":"Crossref","is-referenced-by-count":0,"title":["VideoSetDiff: Identifying and Reasoning Similarities and Differences in Similar Videos"],"prefix":"10.1109","author":[{"given":"Yue","family":"Qiu","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjun","family":"Sun","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Yagi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shusaku","family":"Egami","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natsuki","family":"Miyata","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ken","family":"Fukuda","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kensho","family":"Hara","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryusuke","family":"Sagawa","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1075\/gest.9.3.06coo"},{"key":"ref2","article-title":"Beyond categories: The visual memex model for reasoning about object relationships","author":"Malisiewicz","year":"2009","journal-title":"NeurIPS, 22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195395518.003.0010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01773"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01927"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref10","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref11","article-title":"Google","year":"2023","journal-title":"Gemini"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref14","first-page":"2630","article-title":"Howto 100 m: Learning a text-video embedding by watching hundred million narrated video clips","author":"Miech","year":"2019","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01338"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00663"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"ref23","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref29","author":"Kollias","year":"2018","journal-title":"Aff-wild2: Extending the aff-wild database for affect recognition"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02069"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00627"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref35","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume":"35","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00600"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02063"},{"key":"ref38","author":"Li","year":"2023","journal-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension"},{"key":"ref39","author":"Tong","year":"2024","journal-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 1 lms"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01271"},{"key":"ref43","author":"Wang","year":"2023","journal-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref45","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref47","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS, 36"},{"key":"ref48","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"CoRR"},{"key":"ref49","author":"Cheng","year":"2024","journal-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref54","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2188"},{"key":"ref56","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"issue":"2","key":"ref57","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444633.pdf?arnumber=11444633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:17Z","timestamp":1777531577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01138","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}