{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:18:19Z","timestamp":1783527499499,"version":"3.55.0"},"reference-count":168,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NRF Fellowship for AI","award":["NRF-NRFFAI1-2019-0001"],"award-info":[{"award-number":["NRF-NRFFAI1-2019-0001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3327284","type":"journal-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T17:51:51Z","timestamp":1698169911000},"page":"1011-1030","source":"Crossref","is-referenced-by-count":91,"title":["Temporal Action Segmentation: An Analysis of Modern Techniques"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6080-5220","authenticated-orcid":false,"given":"Guodong","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-6005","authenticated-orcid":false,"given":"Fadime","family":"Sener","sequence":"additional","affiliation":[{"name":"Meta Reality Labs, Burlingame, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref4","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Patrick"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s19051005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986861"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07102-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62392-4_30"},{"key":"ref10","article-title":"Deep learning for vision-based prediction: A survey","author":"Rasouli","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.140"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00627"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref17","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"Jiang","year":"2014"},{"key":"ref18","first-page":"185","article-title":"Segmenting motion capture data into distinct behaviors","volume-title":"Proc. Graph. Interface","author":"Barbi\u010d"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2008.4813468"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2635030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070827"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOAS742"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_33"},{"key":"ref27","article-title":"Procedure completion by learning from partial summaries","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Naing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref39","article-title":"PIC: Permutation invariant convolution for recognizing long-range activities","author":"Hussein","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref41","first-page":"753","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00798"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01928"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref48","first-page":"7575","article-title":"Egocentric video-language pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref51","article-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20124"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_17"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00634"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00058"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01083"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3231099"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00873"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00332"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2006.160"},{"key":"ref68","article-title":"Deep discriminative clustering analysis","author":"Chang","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00129"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00128"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref77","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref81","first-page":"6508","article-title":"Weakly-supervised action segmentation with iterative soft boundary assignment","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ding"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284080"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"ref86","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref87","article-title":"Vision transformers for action recognition: A survey","author":"Ulhaq","year":"2022"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_20"},{"key":"ref90","article-title":"ASFormer: Transformer for action segmentation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Yi"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"ref92","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-8330-5_4"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_18"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00638"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00027"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01599"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897444"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"ref105","article-title":"TricorNet: A hybrid temporal convolutional and recurrent network for video action segmentation","author":"Ding","year":"2017"},{"key":"ref106","article-title":"Frontal low-rank random tensors for fine-grained action segmentation","author":"Zhang","year":"2019"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.066"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104567"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11133-9"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093535"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"ref113","first-page":"14890","article-title":"Dont pour cereal into coffee: Differentiable temporal logic for temporal action segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108764"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/115"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12678"},{"key":"ref117","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00930","article-title":"Diffusion action segmentation","author":"Liu","year":"2023"},{"key":"ref118","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume-title":"Proc. ECCV THUMOS Workshop","author":"Karaman"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.286"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.338"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.85"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref126","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref127","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.004"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884469"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00366"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3089127"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00829"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00968"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00826"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981351"},{"key":"ref138","article-title":"Robust action segmentation from timestamp supervision","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Souri"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1986.tb01420.x"},{"key":"ref140","article-title":"Learning procedural abstractions and evaluating discrete latent temporal structure","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goel"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00025"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref143","article-title":"TAEC: Unsupervised action segmentation with temporal-aware embedding and clustering","author":"Lin","year":"2023"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506759"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"ref146","article-title":"Permutation-aware action segmentation via unsupervised frame-to-segment alignment","author":"Tran","year":"2023"},{"key":"ref147","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00520"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.507"},{"key":"ref150","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.509"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.231"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959921"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273629"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990935"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"ref161","article-title":"Why cant i dance in the mall? Learning to mitigate scene bias in action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.530"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32695-1_4"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref166","article-title":"Forecasting future action sequences with neural memory networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Gammulle"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01341"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10294187.pdf?arnumber=10294187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T19:09:26Z","timestamp":1730401766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10294187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":168,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3327284","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":[[2024,2]]}}}