{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:10:09Z","timestamp":1793985009356,"version":"4.8.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00787","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8157-8167","source":"Crossref","is-referenced-by-count":1,"title":["VRAgent: Self-Refining Agent for Zero-Shot Multimodal Video Retrieval"],"prefix":"10.1109","author":[{"given":"Ketul","family":"Shah","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pankaj","family":"Nathani","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian Caba","family":"Heilbron","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Media intelligence and search panel"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref3","year":"2024","journal-title":"Use apple intelligence in photos on iphone"},{"key":"ref4","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref5","author":"Castro","year":"2022","journal-title":"Fitclip: Refining large-scale pretrained image-text models for zero-shot video understanding tasks"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_11"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572114"},{"key":"ref9","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref10","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref17","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref18","author":"Jaech","year":"2024","journal-title":"Openai o1 system card"},{"key":"ref19","author":"Jiang","year":"2024","journal-title":"Mixtral of experts"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref21","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref22","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref23","author":"Li","year":"2021","journal-title":"Value: A multi-task benchmark for video-and-language understanding evaluation"},{"key":"ref24","author":"Liu","year":"2024","journal-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01206"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref27","first-page":"36","article-title":"Self-refine: Iterative refinement with self-feedback","author":"Madaan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref29","year":"2021","journal-title":"Building in-video search"},{"key":"ref30","article-title":"Agentic design patterns part 1: Four ai agent strategies that improve gpt-4 and gpt-3.5 performance","author":"Ng","year":"2024","journal-title":"The Batch"},{"key":"ref31","author":"Patil","year":"2023","journal-title":"Gorilla: Large language model connected with massive apis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"ref36","first-page":"36","article-title":"Toolformer: Language models can teach themselves to use tools","author":"Schick","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","article-title":"A multimodal automated interpretability agent","volume-title":"Forty-first International Conference on Machine Learning","author":"Shaham"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/jj.19985101.13"},{"key":"ref40","first-page":"1","article-title":"Learning text-to-video retrieval from image captioning","author":"Ventura","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref48","author":"Xue","year":"2022","journal-title":"Clip-vip: Adapting pretrained image-text model to video-language representation alignment"},{"key":"ref49","article-title":"Large language models as optimizers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref51","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491984.pdf?arnumber=11491984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:31Z","timestamp":1778046811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00787","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}