{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:16:43Z","timestamp":1768281403914,"version":"3.49.0"},"reference-count":71,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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","award":["U23A20387"],"award-info":[{"award-number":["U23A20387"]}],"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","award":["62322212"],"award-info":[{"award-number":["62322212"]}],"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","award":["62072455"],"award-info":[{"award-number":["62072455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Pengcheng Laboratory Research Project","award":["PCL2025AS14"],"award-info":[{"award-number":["PCL2025AS14"]}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0112200"],"award-info":[{"award-number":["2021ZD0112200"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3632652","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:50:18Z","timestamp":1763146218000},"page":"853-864","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Learning of Instance-Level Proxy Semantics for Few-Shot Action Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3948-7413","authenticated-orcid":false,"given":"Fang","family":"Peng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01238"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2984710"},{"key":"ref8","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00855"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref11","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref15","article-title":"EZ-CLIP: Efficient zeroshot video action recognition","author":"Ahmad","year":"2023"},{"key":"ref16","first-page":"26462","article-title":"ST-Adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pan","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658044"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111902"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref23","first-page":"21981","article-title":"CrossTransformers: Spatially-aware few-shot transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Doersch","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273459"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref31","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref32","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref34","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref35","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2902431"},{"key":"ref40","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Karras","year":"2022"},{"key":"ref41","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref43","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref45","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"issue":"47","key":"ref46","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3341437"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref53","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/181"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128649"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref62","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110948"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03427-x"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110110"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02017-7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00633"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_11"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11249424.pdf?arnumber=11249424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:15Z","timestamp":1768255335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3632652","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}