{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:45:44Z","timestamp":1777657544155,"version":"3.51.4"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"State Key Research and Development Program","award":["2016YFB1001003"],"award-info":[{"award-number":["2016YFB1001003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976137"],"award-info":[{"award-number":["61976137"]}],"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":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MoE-China Mobile Research Fund Project","award":["MCM20180702"],"award-info":[{"award-number":["MCM20180702"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B07022"],"award-info":[{"award-number":["B07022"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["150633"],"award-info":[{"award-number":["150633"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012656","name":"Shanghai Key Laboratory of Digital Media Processing and Transmission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012656","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SJTU-BIGO Joint Research Fund"},{"name":"CCF-Tencent Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,2,1]]},"DOI":"10.1109\/tpami.2019.2946823","type":"journal-article","created":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T20:09:46Z","timestamp":1570824586000},"page":"666-683","source":"Crossref","is-referenced-by-count":16,"title":["Fine-Grained Video Captioning via Graph-based Multi-Granularity Interaction Learning"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-0891","authenticated-orcid":false,"given":"Ning","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-028X","authenticated-orcid":false,"given":"Bingbing","family":"Ni","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4410-3741","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7468-8790","authenticated-orcid":false,"given":"Minghao","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-1362","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7170-3884","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4477-9875","authenticated-orcid":false,"given":"Shuo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5165-4325","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Texas at San Antonio, San Antonio, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-1182","authenticated-orcid":false,"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.79"},{"key":"ref2","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2015","journal-title":"Proc. 3rd Int. Conf. Learn. Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0480"},{"key":"ref6","article-title":"Hierarchical learning: Theory with applications in speech and vision","author":"Bouvrie","year":"2009"},{"key":"ref7","article-title":"Realtime multi-person 2D pose estimation using part affinity fields","author":"Cao","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11849"},{"key":"ref10","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126306"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991218"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275110"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref28","article-title":"Pointsift: A sift-like network module for 3D point cloud semantic segmentation","author":"Jiang","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"ref33","first-page":"301","article-title":"Hierarchical reinforcement learning with parameters","volume-title":"Proc. Conf. Robot Learn.","author":"Klimek","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2609811"},{"issue":"2","key":"ref35","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","article-title":"Natural language description of human activities from video images based on concept hierarchy of actions","volume":"50","author":"Kojima","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref40","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proc. EMNLP Workshop Statistical Mach. Transl.","author":"Lavie"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.154"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487305"},{"key":"ref43","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_13"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00174"},{"key":"ref51","first-page":"2277","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"Newell","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst."},{"key":"ref52","first-page":"2274","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Newell"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.102"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref57","first-page":"77","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref58","first-page":"5099","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.320"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180234"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2005.869771"},{"key":"ref67","article-title":"Attention for fine-grained categorization","author":"Sermanet","year":"2015","journal-title":"Proc. 3rd Int. Conf. Learn. Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.128"},{"key":"ref70","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref72","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30618-1_17"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40760-4_43"},{"key":"ref75","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","volume-title":"Proc. 25th Int. Conf. Comput. Linguistics","author":"Thomason"},{"key":"ref76","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances Neural Inf. Process. Syst."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00484"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref88","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123358"},{"key":"ref90","first-page":"3122","article-title":"Unsupervised template learning for fine-grained object recognition","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00629"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.662"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9674188\/08865609.pdf?arnumber=8865609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:41:52Z","timestamp":1749231712000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8865609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":95,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2946823","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,1]]}}}