{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:02Z","timestamp":1777865342290,"version":"3.51.4"},"reference-count":62,"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\/iccv51701.2025.02165","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23321-23331","source":"Crossref","is-referenced-by-count":0,"title":["PVChat: Personalized Video Chat with One-Shot Learning"],"prefix":"10.1109","author":[{"given":"Yufei","family":"Shi","sequence":"first","affiliation":[{"name":"MedVisAI Lab"}]},{"given":"Weilong","family":"Yan","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Gang","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}]},{"given":"Yumeng","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University"}]},{"given":"Yucheng","family":"Chen","sequence":"additional","affiliation":[{"name":"MedVisAI Lab"}]},{"given":"Zhenxi","family":"Li","sequence":"additional","affiliation":[{"name":"MedVisAI Lab"}]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}]},{"given":"Si Yong","family":"Yeo","sequence":"additional","affiliation":[{"name":"MedVisAI Lab"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_5"},{"key":"ref3","article-title":"Anthropic","volume-title":"The claude 3 model family: Opus, sonnet","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref5","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref7","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref8","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref11","article-title":"Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timoth\u00e9e Lacroix, and William El Sayed","author":"Q","year":"2023","journal-title":"Mistral 7b"},{"key":"ref12","article-title":"Moh: Multihead attention as mixture-of-head attention","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2789"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref16","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref17","article-title":"Llava-surg: towards multimodal surgical assistant via structured surgical video learning","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref20","article-title":"The lazy neuron phenomenon: On emergence of activation sparsity in transformers","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref23","article-title":"Videoteller: Enhancing cross-modal generation with fusion and decoupling","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref26","author":"Liu","year":"2024","journal-title":"Llavanext: Improved reasoning, ocr, and world knowledge"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3338269"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.131"},{"key":"ref29","article-title":"Points: Improving your visionlanguage model with affordable strategies","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref34","first-page":"40913","article-title":"Yo\u2019llava: Your personalized language and vision assistant","volume":"37","author":"Nguyen","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"40913","article-title":"Yo\u2019llava: Your personalized language and vision assistant","volume":"37","author":"Nguyen","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Godel: Large-scale pre-training for goal-directed dialog","author":"Peng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Deepfacelab: Integrated, flexible and extensible face-swapping framework","author":"Perov","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Personalized large vision-language models","author":"Pham","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Personalized visual instruction tuning","author":"Pi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref44","article-title":"Prosparse: Introducing and enhancing intrinsic activation sparsity within large language models","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref46","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"87310","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref50","article-title":"Chatvideo: A trackletcentric multimodal and versatile video understanding system","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref52","article-title":"Remoe: Fully differentiable mixture-of-experts with relu routing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref55","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref57","article-title":"Identitypreserving text-to-video generation by frequency decomposition","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3347693"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33160"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"}],"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\/11446035.pdf?arnumber=11446035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:52Z","timestamp":1777529872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02165","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}