{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:43:27Z","timestamp":1760420607360,"version":"build-2065373602"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"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"}]},{"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":[[2025,5,23]]},"DOI":"10.1109\/icmlt65785.2025.11193324","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:39:05Z","timestamp":1760377145000},"page":"488-494","source":"Crossref","is-referenced-by-count":0,"title":["VideoMamba-LLaVA: Efficient Video Question Answering with Selective Scanning and Lightweight Inference"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhu","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanming","family":"Guo","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Mamba: Linear-time sequence modeling with selective state spaces","year":"2023","author":"Gu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"article-title":"Audiovisual slowfast networks for video recognition","year":"2020","author":"Xiao","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"article-title":"Convnet architecture search for spatiotemporal feature learning","year":"2017","author":"Tran","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"article-title":"Large-scale video classification guided by batch normalized lstm translator","year":"2017","author":"Yoo","key":"ref9"},{"key":"ref10","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","volume-title":"International conference on machine learning","author":"Srivastava"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.25.4.043010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079030"},{"article-title":"Hybrid spiking neural network \u2013 transformer video classification model","year":"2024","author":"Bateni","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107814"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3556223.3556241"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475703"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","year":"2024","author":"Chen","key":"ref20"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref21"},{"key":"ref22","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pb-llm: Partially binarized large language models","year":"2023","author":"Shang","key":"ref23"},{"article-title":"Mobilevlm : A fast, strong and open vision language assistant for mobile devices","year":"2023","author":"Chu","key":"ref24"},{"issue":"3","key":"ref25","first-page":"3","article-title":"Phi-2: The surprising power of small language models","volume":"1","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref26","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"Videochat: Chat-centric video understanding","year":"2023","author":"Li","key":"ref27"},{"issue":"3","key":"ref28","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"article-title":"Valley: Video assistant with large language model enhanced ability","year":"2023","author":"Luo","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref32","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"}],"event":{"name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","start":{"date-parts":[[2025,5,23]]},"location":"Helsinki, Finland","end":{"date-parts":[[2025,5,25]]}},"container-title":["2025 10th International Conference on Machine Learning Technologies (ICMLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192828\/11192850\/11193324.pdf?arnumber=11193324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:10:13Z","timestamp":1760418613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icmlt65785.2025.11193324","relation":{},"subject":[],"published":{"date-parts":[[2025,5,23]]}}}