{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:36Z","timestamp":1761894576110,"version":"build-2065373602"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209249","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Instruction-aware Memory Network for Video Recognition"],"prefix":"10.1109","author":[{"given":"Bimei","family":"Wang","sequence":"first","affiliation":[{"name":"Jinan University,College of Cyber Security,China"}]},{"given":"Haijiang","family":"Li","sequence":"additional","affiliation":[{"name":"Lanzhou Jiaotong University,School of Electronic Information Engineering,China"}]},{"given":"Jisheng","family":"Dang","sequence":"additional","affiliation":[{"name":"Lanzhou University,School of Information Science & Engineering,China"}]},{"given":"Yun","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of HongKong,College of Computing,China"}]},{"given":"Zhixuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,China"}]},{"given":"Jiyuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,China"}]},{"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Faculty of Engineering,China"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Lanzhou Jiaotong University,School of Electronic Information Engineering,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3418522"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277389"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3498735"},{"issue":"3","key":"ref6","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref10","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref11","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"Chen","year":"2011","journal-title":"ACL HLT"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_22"},{"key":"ref13","first-page":"38154","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume":"36","author":"Shen","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3421623"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3280389"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3357118"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3341457"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3423390"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69525-5_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413879"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3167910"},{"article-title":"Video-teller: Enhancing cross-modal generation with fusion and decoupling","year":"2023","author":"Liu","key":"ref30"},{"key":"ref31","first-page":"38728","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","volume-title":"ICML","author":"Xu"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv36zrf8.5"},{"key":"ref35","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209249.pdf?arnumber=11209249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:47Z","timestamp":1761888647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209249","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}