{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:13:34Z","timestamp":1782260014018,"version":"3.54.5"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887668","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Wang","sequence":"first","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1070"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11944"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449892"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41682-8_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01189-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16203"},{"key":"ref18","volume-title":"Sports-qa: A large-scale video question answering benchmark for complex and professional sports","author":"Li","year":"2024"},{"issue":"02858","key":"ref19","volume-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding","volume":"2306","author":"Zhang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448079"},{"key":"ref21","author":"Radford","year":"2022","journal-title":"Robust speech recognition via large-scale weak supervision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref26","volume-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023"},{"issue":"15389","key":"ref27","volume":"2303","author":"Sun","year":"2023","journal-title":"Eva-clip: Improved training techniques for clip at scale"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"issue":"06355","key":"ref30","volume":"2305","author":"Li","year":"2023","journal-title":"Videochat: Chat-centric video understanding"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref32","article-title":"Vitae: Vision transformer advanced by exploring intrinsic inductive bias","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"08774","key":"ref33","volume":"2303","year":"2023","journal-title":"OpenAI: Gpt-4 technical report"},{"issue":"09288","key":"ref34","volume":"2307","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478328"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887668.pdf?arnumber=10887668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:13Z","timestamp":1774416373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887668","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}