{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:22Z","timestamp":1778171062271,"version":"3.51.4"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62222207"],"award-info":[{"award-number":["62222207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211520"],"award-info":[{"award-number":["BK20211520"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0151"],"award-info":[{"award-number":["2023TQ0151"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M731596"],"award-info":[{"award-number":["2023M731596"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["14380109"],"award-info":[{"award-number":["14380109"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["14913211"],"award-info":[{"award-number":["14913211"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3384392","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T17:57:58Z","timestamp":1712167078000},"page":"3039-3053","source":"Crossref","is-referenced-by-count":15,"title":["Appearance-Agnostic Representation Learning for Compositional Action Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4102-6506","authenticated-orcid":false,"given":"Peng","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-9458","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhewei","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Application of segment anything model for civil infrastructure defect assessment","author":"Ahmadi","year":"2023","journal-title":"arXiv:2304.12600"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612031"},{"key":"ref6","article-title":"SAM on medical images: A comprehensive study on three prompt modes","author":"Cheng","year":"2023","journal-title":"arXiv:2305.00035"},{"key":"ref7","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref9","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref14","article-title":"Segment anything model (SAM) meets glass: Mirror and transparent objects cannot be easily detected","author":"Han","year":"2023","journal-title":"arXiv:2305.00278"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3221292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref17","article-title":"Scalable mask annotation for video text spotting","author":"He","year":"2023","journal-title":"arXiv:2305.01443"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref21","article-title":"SAFCAR: Structured attention fusion for compositional action recognition","author":"Soo Kim","year":"2020","journal-title":"arXiv:2012.02109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01283"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref26","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":"ref27","article-title":"UniFormerV2: Spatiotemporal learning by arming image ViTs with video UniFormer","author":"Li","year":"2022","journal-title":"arXiv:2211.09552"},{"key":"ref28","first-page":"21158","article-title":"Neural-logic human-object interaction detection","volume-title":"Proc. Adv. Neural Inf. Process. Systems (NeurIPS)","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6811"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064379"},{"key":"ref39","article-title":"Segment anything in medical images","author":"Ma","year":"2023","journal-title":"arXiv:2304.12306"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222305"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.129"},{"key":"ref43","volume-title":"GPT-4V(ision) System Card","year":"2023"},{"key":"ref44","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Patrick"},{"key":"ref45","first-page":"581","article-title":"Action recognition with stacked Fisher vectors","volume-title":"Proc. 13th Eur. Conf. Comput. Vis. (ECCV)","author":"Peng"},{"key":"ref46","first-page":"110","article-title":"Revisiting spatio-temporal layouts for compositional action recognition","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Radevski"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref48","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref50","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Simonyan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"ref54","article-title":"Can SAM segment anything? When SAM meets camouflaged object detection","author":"Tang","year":"2023","journal-title":"arXiv:2304.04709"},{"key":"ref55","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tong"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref64","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023","journal-title":"arXiv:2305.02677"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338078"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408923"},{"key":"ref68","article-title":"Edit everything: A text-guided generative system for images editing","author":"Xie","year":"2023","journal-title":"arXiv:2304.14006"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547862"},{"key":"ref70","article-title":"Interactive fusion of multi-level features for compositional activity recognition","author":"Yan","year":"2020","journal-title":"arXiv:2012.05689"},{"key":"ref71","first-page":"1","article-title":"Fine-grained visual prompting","volume-title":"Proc. Adv. Neural Inf. Process. Systems (NeurIPS)","author":"Yang"},{"key":"ref72","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv:2304.06790"},{"key":"ref73","first-page":"1976","article-title":"Is an object-centric video representation beneficial for transfer?","volume-title":"Proc. Asian Conf. Comput. Vision (ACCV)","author":"Zhang"},{"key":"ref74","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"ref76","article-title":"Towards segment anything model (SAM) for medical image segmentation: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2305.03678"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3182866"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3189811"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10949577\/10488474.pdf?arnumber=10488474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:13:15Z","timestamp":1744063995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10488474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":80,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3384392","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}