{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:36:04Z","timestamp":1730266564448,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10649977","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["MemoTiChat: A Memory-Augmented Time-Sensitive Model for Ultra-Long Video Understanding"],"prefix":"10.1109","author":[{"given":"Jianlong","family":"Hou","sequence":"first","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tao","sequence":"additional","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelian","family":"Ding","sequence":"additional","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Information Technology Center,China Mobile,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Introducing chatgpt","year":"2022","key":"ref1"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","volume":"abs\/2302.13971","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref3","article-title":"Moviechat: From dense token to sparse memory for long video understanding","volume":"abs\/2307.16449","author":"Song","year":"2023","journal-title":"CoRR"},{"key":"ref4","article-title":"Timechat: A time-sensitive multimodal large language model for long video understanding","volume":"abs\/2312.02051","author":"Ren","year":"2023","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref8","article-title":"Clip2video: Mastering video-text retrieval via image CLIP","volume":"abs\/2106.11097","author":"Fang","year":"2021","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref11"},{"key":"ref12","article-title":"Videochat: Chat-centric video understanding","volume":"abs\/2305.06355","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"ref18","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021","author":"Nagrani"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref23","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems NeurIPS 2021","author":"Xu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"ref26","article-title":"Negative sample matters: A renaissance of metric learning for temporal grounding","volume":"abs\/2109.04872","author":"Wang","year":"2021","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01590"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy","key":"ref29"},{"article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Li","key":"ref30"},{"journal-title":"NeurIPS 2022","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","key":"ref31"},{"key":"ref32","article-title":"FETV: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume":"abs\/2311.01813","author":"Liu","journal-title":"CoRR"},{"key":"ref33","article-title":"Lora: Low-rank adaptation of large language models","volume":"abs\/2106.09685","author":"Hu","year":"2021","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref36","article-title":"Qvhighlights: Detecting moments and highlights in videos via natural language queries","volume":"abs\/2107.09609","author":"Lei","year":"2021","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.257"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref39","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"abs\/2305.06500","author":"Dai","year":"2023","journal-title":"CoRR"},{"key":"ref40","article-title":"EVA-CLIP: improved training techniques for CLIP at scale","volume":"abs\/2303.15389","author":"Sun","year":"2023","journal-title":"CoRR"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref41"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10649977.pdf?arnumber=10649977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:53:09Z","timestamp":1725943989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10649977","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}