{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T19:34:57Z","timestamp":1781811297435,"version":"3.54.5"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210102","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":1,"title":["Enhancing Long Video Understanding via Hierarchical Event-Based Memory"],"prefix":"10.1109","author":[{"given":"Dingxin","family":"Cheng","sequence":"first","affiliation":[{"name":"Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingda","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Guo","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (Shenzhen),School of Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingbin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref2","first-page":"38728","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","author":"Xu","year":"2023","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105168"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref10","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3604614"},{"key":"ref14","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref15","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":"ref16","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref18","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref21","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref24","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023"},{"key":"ref25","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref31","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref32","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"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\/11210102.pdf?arnumber=11210102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:28Z","timestamp":1761888808000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210102","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}