{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:10:12Z","timestamp":1778789412299,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["JP25H01116"],"award-info":[{"award-number":["JP25H01116"]}]},{"name":"China Scholarship Council during the doctoral study at Kyushu University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3691141","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:54:26Z","timestamp":1778183666000},"page":"70089-70101","source":"Crossref","is-referenced-by-count":0,"title":["Reasoning-Enhanced Few-Shot Human Activity Recognition via Visual Reinforcement Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0543-7789","authenticated-orcid":false,"given":"Wenqi","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Information Science and Technology, Graduate School of ISEE, Kyushu University, Fukuoka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-9160","authenticated-orcid":false,"given":"Yutaka","family":"Arakawa","sequence":"additional","affiliation":[{"name":"Department of Information Science and Technology, Graduate School of ISEE, Kyushu University, Fukuoka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15443-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11398-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108061"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s25103072"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref12","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref13","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref14","article-title":"R1-zero\u2019s \u2019aha moment\u2019 in visual reasoning on a 2B non-SFT model","author":"Zhou","year":"2025","journal-title":"arXiv:2503.05132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref16","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref17","article-title":"Valley2: Exploring multimodal models with scalable vision-language design","author":"Wu","year":"2025","journal-title":"arXiv:2501.05901"},{"key":"ref18","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref19","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref20","article-title":"SFT memorizes, RL generalizes: A comparative study of foundation model post-training","author":"Chu","year":"2025","journal-title":"arXiv:2501.17161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ICMU65253.2025.11219147"},{"key":"ref23","article-title":"R1-omni: Explainable omni-multimodal emotion recognition with reinforcement learning","author":"Zhao","year":"2025","journal-title":"arXiv:2503.05379"},{"key":"ref24","article-title":"VideoChat-r1: Enhancing spatio-temporal perception via reinforcement fine-tuning","author":"Li","year":"2025","journal-title":"arXiv:2504.06958"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref26","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref27","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv:2402.03300"},{"key":"ref28","article-title":"Surveying the MLLM landscape: A meta-review of current surveys","author":"Li","year":"2024","journal-title":"arXiv:2409.18991"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref30","article-title":"Efficient multimodal large language models: A survey","author":"Jin","year":"2024","journal-title":"arXiv:2405.10739"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121372"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111497"},{"key":"ref33","article-title":"OpenAI o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv:2412.16720"},{"key":"ref34","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref35","article-title":"OpenVLThinker: An early exploration to complex vision-language reasoning via iterative self-improvement","author":"Deng","year":"2025","journal-title":"arXiv:2503.17352"},{"key":"ref36","article-title":"Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model","author":"Hu","year":"2025","journal-title":"arXiv:2503.24290"},{"key":"ref37","article-title":"DAPO: An open-source LLM reinforcement learning system at scale","author":"Yu","year":"2025","journal-title":"arXiv:2503.14476"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-012-0450-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref43","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref44","article-title":"ViSurf: Visual supervised-and-reinforcement fine-tuning for large vision-and-language models","author":"Liu","year":"2025","journal-title":"arXiv:2510.10606"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11511694.pdf?arnumber=11511694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:58:55Z","timestamp":1778788735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11511694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3691141","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}