{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T19:29:46Z","timestamp":1787772586390,"version":"build-2784847793"},"reference-count":85,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Funds for NSFC Project","award":["62572072"],"award-info":[{"award-number":["62572072"]}]},{"name":"Beijing Natural Science Foundation","award":["L243027"],"award-info":[{"award-number":["L243027"]}]},{"name":"Hainan Provincial Joint Project of Li\u2019an International Education Innovation Pilot Zone","award":["626LALH006"],"award-info":[{"award-number":["626LALH006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3723718","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:02:50Z","timestamp":1787166170000},"page":"9028-9041","source":"Crossref","is-referenced-by-count":0,"title":["Chain-of-Evidence Multimodal Reasoning for Few-Shot Temporal Action Localization"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6955-6635","authenticated-orcid":false,"given":"Mengshi","family":"Qi","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4225-033X","authenticated-orcid":false,"given":"Hongwei","family":"Ji","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wulian","family":"Yun","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3905-2062","authenticated-orcid":false,"given":"Xianlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref9","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref12","article-title":"A closer look at few-shot classification","author":"Chen","year":"2019","journal-title":"arXiv:1904.04232"},{"key":"ref13","article-title":"A baseline for few-shot image classification","author":"Dhillon","year":"2019","journal-title":"arXiv:1909.02729"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_30"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01577"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.101"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00626"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00937"},{"key":"ref20","article-title":"Videochat-flash: Hierarchical compression for long-context video modeling","author":"Li","year":"2024","journal-title":"arXiv:2501.00574"},{"key":"ref21","article-title":"InternVideo2.5: Empowering video MLLMs with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv:2501.12386"},{"key":"ref22","article-title":"Qwen2.5-vl technical report","volume-title":"arXiv2502.13923","author":"Bai","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01771"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8996591"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3613952"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00839"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0546"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00408"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983567"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3627224"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3627091"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01603"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755868"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00786"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3646919"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2026.3700882"},{"key":"ref45","first-page":"21231","article-title":"Towards balanced multi-modal learning in 3D human pose estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref46","first-page":"39282","article-title":"Robo-SGG: Exploiting layout-oriented normalization and restitution can improve robust scene graph generation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Lv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119618"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103926"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00616"},{"key":"ref50","article-title":"Gpt-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref51","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref53","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref54","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref55","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref57","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2026.3652360"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2026.3663210"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3549351"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3581039"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2026.113929"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref65","first-page":"18639","article-title":"Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Liu"},{"key":"ref66","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01026"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_33"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref72","article-title":"Thumos challenge: Action recognition with a large number of classes","author":"Jiang","year":"2014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2856"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref79","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref82","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref84","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref85","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Hui","year":"2024"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11659823.pdf?arnumber=11659823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T19:04:52Z","timestamp":1787771092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11659823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3723718","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}