{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:58:47Z","timestamp":1778788727826,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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":[[2025,9,10]]},"DOI":"10.23919\/icmu65253.2025.11219147","type":"proceedings-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:48:44Z","timestamp":1762454924000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Few-Shot Vision-Based Human Activity Recognition with MLLM-Based Visual Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Wenqi","family":"Zheng","sequence":"first","affiliation":[{"name":"Kyushu University,Graduate School and Faculty of Information Science and Electrical Engineering,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutaka","family":"Arakawa","sequence":"additional","affiliation":[{"name":"Kyushu University,Graduate School and Faculty of Information Science and Electrical Engineering,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ICMU58504.2023.10412222"},{"key":"ref3","author":"Deng","year":"2025","journal-title":"Openvlthinker: An early exploration to complex vision-language reasoning via iterative self-improvement"},{"key":"ref4","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref5","author":"Hu","year":"2025","journal-title":"Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model"},{"key":"ref6","author":"Jin","year":"2024","journal-title":"Efficient multimodal large language models: A survey"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref8","author":"Kumar","year":"2025","journal-title":"Llm post-training: A deep dive into reasoning large language models"},{"key":"ref9","author":"Li","year":"2024","journal-title":"Surveying the mllm landscape: A meta-review of current surveys"},{"key":"ref10","author":"Liu","year":"2025","journal-title":"Visual-rft: Visual reinforcement finetuning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3406737"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-012-0450-4"},{"key":"ref14","author":"Shen","year":"2025","journal-title":"Vlm-r1: A stable and generalizable r1-style large vision-language model"},{"key":"ref15","author":"Soomro","year":"2012","journal-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ICMU58504.2023.10412226"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3357591"},{"key":"ref20","author":"Zhao","year":"2025","journal-title":"R1-omni: Explainable omnimultimodal emotion recognition with reinforcement learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3411061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3352400"}],"event":{"name":"2025 Fifteenth International Conference on Mobile Computing and Ubiquitous Networking (ICMU)","location":"Busan, Korea, Republic of","start":{"date-parts":[[2025,9,10]]},"end":{"date-parts":[[2025,9,12]]}},"container-title":["2025 Fifteenth International Conference on Mobile Computing and Ubiquitous Networking (ICMU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11219022\/11219106\/11219147.pdf?arnumber=11219147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T06:54:43Z","timestamp":1762498483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11219147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.23919\/icmu65253.2025.11219147","relation":{},"subject":[],"published":{"date-parts":[[2025,9,10]]}}}