{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:27:09Z","timestamp":1787660829749,"version":"build-2736575974"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007128","name":"Shaanxi Province Natural Science Foundation","doi-asserted-by":"publisher","award":["2024JC-YBMS-480"],"award-info":[{"award-number":["2024JC-YBMS-480"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52339003"],"award-info":[{"award-number":["52339003"]}],"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":["62273273"],"award-info":[{"award-number":["62273273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.image.2026.117648","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:53:13Z","timestamp":1783061593000},"page":"117648","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A point-supervised temporal action localization method based on category feature memory enhancement and dual classifiers"],"prefix":"10.1016","volume":"148","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6672-7948","authenticated-orcid":false,"given":"Fan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangfeng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobing","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.image.2026.117648_bib0001","doi-asserted-by":"crossref","first-page":"8535","DOI":"10.1109\/TIP.2020.3016486","article-title":"Revisiting anchor mechanisms for temporal action localization","volume":"29","author":"Yang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117648_bib0002","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"10156","article-title":"G-TAD: subgraph localization for temporal action detection","author":"Xu","year":"2020"},{"key":"10.1016\/j.image.2026.117648_bib0003","doi-asserted-by":"crossref","first-page":"4746","DOI":"10.1109\/TIP.2022.3182866","article-title":"A temporal-aware relation and attention network for temporal action localization","volume":"31","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117648_bib0004","series-title":"IEEE International Conference on Computer Vision ICCV","first-page":"7982","article-title":"Foreground-action consistency network for weakly supervised temporal action localization","author":"Huang","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0005","series-title":"29th ACM International Conference on Multimedia","first-page":"1591","article-title":"Cross-modal consensus network for weakly supervised temporal action localization","author":"Hong","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0006","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"3272","article-title":"Weakly supervised temporal action localization via representative snippet knowledge propagation","author":"Huang","year":"2022"},{"key":"10.1016\/j.image.2026.117648_bib0007","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"13925","article-title":"Asm-loc: action-aware segment modeling for weakly-supervised temporal action localization","author":"He","year":"2022"},{"key":"10.1016\/j.image.2026.117648_bib0008","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"2394","article-title":"Proposal-based multiple instance learning for weakly-supervised temporal action localization","author":"Ren","year":"2023"},{"key":"10.1016\/j.image.2026.117648_bib0009","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"22992","article-title":"PivoTAL: prior-driven supervision for weakly-supervised temporal action localization","author":"Rizve","year":"2023"},{"key":"10.1016\/j.image.2026.117648_bib0010","series-title":"IEEE International Conference on Computer Vision ICCV","first-page":"13628","article-title":"Learning action completeness from points for weakly-supervised temporal action localization","author":"Lee","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0011","doi-asserted-by":"crossref","first-page":"7363","DOI":"10.1109\/TIP.2022.3222623","article-title":"Compact representation and reliable classification learning for point-level weakly-supervised action localization","volume":"31","author":"Fu","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117648_bib0012","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"18440","article-title":"Realigning confidence with temporal saliency information for point-level weakly-supervised temporal action localization","author":"Xia","year":"2024"},{"key":"10.1016\/j.image.2026.117648_bib0013","series-title":"European Conference on Computer Vision","first-page":"420","article-title":"SF-net: single-frame supervision for temporal action localization","author":"Ma","year":"2020"},{"key":"10.1016\/j.image.2026.117648_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118965","article-title":"Prototype contrastive learning for point-supervised temporal action detection","volume":"213","author":"Li","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.image.2026.117648_bib0015","doi-asserted-by":"crossref","first-page":"2419","DOI":"10.1109\/TIP.2024.3378477","article-title":"Neighbor-guided pseudo-label generation and refinement for single-frame supervised temporal action localization","volume":"33","author":"Li","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117648_bib0016","first-page":"7115","article-title":"HR-Pro: Point-supervised temporal action localization via hierarchical reliability propagation","volume":"38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.image.2026.117648_bib0017","series-title":"IEEE International Conference on Computer Vision ICCV","first-page":"13455","article-title":"Divide and conquer for single-frame temporal action localization","author":"Ju","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0018","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"394","article-title":"FBI-TAL: foreground-background integration for single-frame supervised temporal action localization","author":"Dong","year":"2024"},{"key":"10.1016\/j.image.2026.117648_bib0026","series-title":"European Conference on Computer Vision","first-page":"492","article-title":"Actionformer: Localizing moments of actions with transformers","author":"Zhang","year":"2022"},{"key":"10.1016\/j.image.2026.117648_bib0027","series-title":"European Conference on Computer Vision","first-page":"3","article-title":"BSN: Boundary sensitive network for temporal action proposal generation","author":"Lin","year":"2018"},{"key":"10.1016\/j.image.2026.117648_bib0028","series-title":"IEEE International Conference on Computer Vision","first-page":"3889","article-title":"BMN: Boundary-matching network for temporal action proposal generation","author":"Lin","year":"2019"},{"key":"10.1016\/j.image.2026.117648_bib0029","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"485","article-title":"Temporal context aggregation network for temporal action proposal refinement","author":"Qing","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0030","unstructured":"X. Wang, H. Zhang, S. Zhang, Context-aware proposal network for temporal action detection, 2022, arXiv preprint arXiv:2206.09082."},{"key":"10.1016\/j.image.2026.117648_bib0031","unstructured":"X. Wang, Z. Qing, Z. Huang, Y. Feng, S. Zhang, Proposal relation network for temporal action detection, 2021, arXiv preprint arXiv:2106.11812."},{"key":"10.1016\/j.image.2026.117648_bib0041","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"3320","article-title":"Learning salient boundary feature for anchor-free temporal action localization","author":"Lin","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0042","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"18857","article-title":"Tridet: Temporal action detection with relative boundary modeling","author":"Shi","year":"2023"},{"key":"10.1016\/j.image.2026.117648_bib0032","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"19999","article-title":"Fine grained temporal contrastive learning for weakly-supervised temporal action localization","author":"Gao","year":"2022"},{"key":"10.1016\/j.image.2026.117648_bib0033","series-title":"AAAI Conference on Artificial Intelligence","first-page":"1854","article-title":"Weakly-supervised temporal action localization by uncertainty modeling","author":"Lee","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0034","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1109\/TIP.2023.3244411","article-title":"Stochasticformer: stochastic modeling for weakly supervised temporal action localization","volume":"32","author":"Shi","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117648_bib0035","series-title":"European Conference on Computer Vision","first-page":"154","article-title":"Autoloc: weakly-supervised temporal action localization in untrimmed videos","author":"Shou","year":"2018"},{"issue":"4","key":"10.1016\/j.image.2026.117648_bib0036","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2022.3189662","article-title":"Adaptive two-stream consensus network for weakly supervised temporal action localization","volume":"45","author":"Zhai","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2026.117648_bib0037","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"16010","article-title":"Cola: Weakly-supervised temporal action localization with snippet contrastive learning","author":"Zhang","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0038","series-title":"Proceedings of the IEEE Winter Conference on Applications of Computer Vision","first-page":"3213","article-title":"Leaky gated cross-attention for weakly supervised multi-modal temporal action localization","author":"Lee","year":"2022"},{"key":"10.1016\/j.image.2026.117648_bib0039","doi-asserted-by":"crossref","first-page":"8253","DOI":"10.1109\/TMM.2023.3234362","article-title":"A novel action saliency and context-aware network for weakly-supervised temporal action localization","volume":"25","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Multimedia."},{"key":"10.1016\/j.image.2026.117648_bib0040","first-page":"1","article-title":"Action-semantic consistent knowledge for weakly-supervised action localization","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimedia."},{"key":"10.1016\/j.image.2026.117648_bib0025","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"6299","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.image.2026.117648_bib0024","series-title":"Proceeding of the International Conference on Learning Representations","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.image.2026.117648_bib0043","series-title":"IEEE International Conference on Computer Vision ICCV","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.image.2026.117648_bib0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","article-title":"The THUMOS challenge on action recognition for videos in the wild","volume":"155","author":"Idrees","year":"2017","journal-title":"Comput. Vis. Image Understand."},{"key":"10.1016\/j.image.2026.117648_bib0020","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"961","article-title":"Activitynet: a large-scale video benchmark for human activity understanding","author":"Caba Heilbron","year":"2015"},{"key":"10.1016\/j.image.2026.117648_bib0021","series-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR","first-page":"3281","article-title":"Learning to recognize objects in egocentric activities","author":"Fahi","year":"2011"},{"key":"10.1016\/j.image.2026.117648_bib0022","series-title":"Proceedings of the British Machine Vision Conference","first-page":"3","article-title":"You-do, I-learn: discovering task relevant objects and their modes of interaction from multi-user egocentric video","author":"Damen","year":"2014"},{"key":"10.1016\/j.image.2026.117648_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104044","article-title":"POTLoc: pseudo-label oriented transformer for point-supervised temporal action localization","volume":"246","author":"Vahdani","year":"2024","journal-title":"Comput. Vis. Image Understand."}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526001712?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526001712?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:11:49Z","timestamp":1787659909000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596526001712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"alternative-id":["S0923596526001712"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2026.117648","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A point-supervised temporal action localization method based on category feature memory enhancement and dual classifiers","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2026.117648","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"117648"}}