{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:05:39Z","timestamp":1777982739524,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s12559-026-10560-3","type":"journal-article","created":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T02:14:44Z","timestamp":1771640084000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Weakly Supervised Temporal Action Localization Based on Feature Enhancement"],"prefix":"10.1007","volume":"18","author":[{"given":"Hongying","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"issue":"6","key":"10560_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00530-024-01511-9","volume":"30","author":"L Wu","year":"2024","unstructured":"Wu L, Xu L. Local and global context cooperation for temporal action detection. Multimedia Syst. 2024;30(6):1\u201315.","journal-title":"Multimedia Syst"},{"issue":"1","key":"10560_CR2","doi-asserted-by":"publisher","first-page":"2565","DOI":"10.1007\/s11042-023-15196-1","volume":"83","author":"B Wang","year":"2024","unstructured":"Wang B, Song Y, Wang F, Zhao Y, Shu X, Rui Y. Dilation-erosion for single-frame supervised temporal action localization. Multimedia Tools Appl. 2024;83(1):2565\u201387.","journal-title":"Multimedia Tools Appl"},{"issue":"11","key":"10560_CR3","doi-asserted-by":"publisher","first-page":"6939","DOI":"10.1109\/TCSVT.2023.3272891","volume":"33","author":"M Moniruzzaman","year":"2023","unstructured":"Moniruzzaman M, Yin Z. Collaborative foreground, background, and action modeling network for weakly supervised temporal action localization. EEE Trans Circuits Syst Video Technol. 2023;33(11):6939\u201351.","journal-title":"EEE Trans Circuits Syst Video Technol"},{"key":"10560_CR4","doi-asserted-by":"crossref","unstructured":"Shou Z, Gao H, Zhang L, Miyazawa K, Chang S-F. Autoloc: Weakly-supervised temporal action localization in untrimmed videos. In: Proc Eur Conf Comput Vis (ECCV); 2018, p. 154\u201371.","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"10560_CR5","doi-asserted-by":"crossref","unstructured":"Lee P, Uh Y, Byun H. Background suppression network for weakly-supervised temporal action localization. In: Proc AAAI Conf Artif Intell (AAAI); 2020, vol. 34, p. 11320\u20137.","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"10560_CR6","doi-asserted-by":"crossref","unstructured":"Liu D, Jiang T, Wang Y. Completeness modeling and context separation for weakly supervised temporal action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2019, p 1298\u2013307.","DOI":"10.1109\/CVPR.2019.00139"},{"key":"10560_CR7","doi-asserted-by":"crossref","unstructured":"Zhou J, Wu Y. Temporal feature enhancement dilated convolution network for weakly-supervised temporal action localization. In: Proc IEEE\/CVF Winter Conf Appl Comput Vis (WACV); 2023, p. 6028\u201337.","DOI":"10.1109\/WACV56688.2023.00597"},{"key":"10560_CR8","unstructured":"Liu Y, Li X, Luo Z, Zhou W. Jcdnet: Joint of common and definite phases network for weakly supervised temporal action localization. 2023. arXiv:2303.17294."},{"key":"10560_CR9","doi-asserted-by":"crossref","unstructured":"Zhao Y, Xiong Y, Wang L, Wu Z, Tang X, Lin D. Temporal action detection with structured segment networks. In: Proc IEEE Int Conf Comput Vis (ICCV); 2017, p. 2914\u201323.","DOI":"10.1109\/ICCV.2017.317"},{"key":"10560_CR10","doi-asserted-by":"crossref","unstructured":"Gao J, Yang Z, Chen K, Sun C, Nevatia R. Turn tap: Temporal unit regression network for temporal action proposals. In: Proc. IEEE Int Conf Comput Vis (ICCV); 2017, p. 3628\u201336.","DOI":"10.1109\/ICCV.2017.392"},{"key":"10560_CR11","doi-asserted-by":"crossref","unstructured":"Chao Y-W, Vijayanarasimhan S, Seybold B, Ross DA, Deng J, Sukthankar R. Rethinking the faster r-cnn architecture for temporal action localization. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2018 p. 1130\u20139.","DOI":"10.1109\/CVPR.2018.00124"},{"key":"10560_CR12","doi-asserted-by":"crossref","unstructured":"Zeng R, Huang W, Tan M, Rong Y, Zhao P, Huang J, Gan C. Graph convolutional networks for temporal action localization. In: Proc IEEE\/CVF Int Conf Comput Vis (ICCV); 2019 p. 7094\u2013103.","DOI":"10.1109\/ICCV.2019.00719"},{"key":"10560_CR13","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M. Bsn: Boundary sensitive network for temporal action proposal generation. In: Proc Eur Conf Comput Vis (ECCV); 2018 p. 3\u201319.","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"10560_CR14","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S. Bmn: Boundary-matching network for temporal action proposal generation. In: Proc IEEE\/CVF Int Conf Comput Vis (ICCV); 2019 p. 3889\u201398.","DOI":"10.1109\/ICCV.2019.00399"},{"key":"10560_CR15","doi-asserted-by":"publisher","first-page":"8535","DOI":"10.1109\/TIP.2020.3016486","volume":"29","author":"L Yang","year":"2020","unstructured":"Yang L, Peng H, Zhang D, Fu J, Han J. Revisiting anchor mechanisms for temporal action localization. IEEE Trans Image Process. 2020;29:8535\u201348.","journal-title":"IEEE Trans Image Process"},{"key":"10560_CR16","unstructured":"Buch S, Escorcia V, Ghanem B, Fei-Fei L, Niebles JC. End-to-end, single-stream temporal action detection in untrimmed videos. 2019."},{"key":"10560_CR17","doi-asserted-by":"crossref","unstructured":"Long F, Yao T, Qiu Z, Tian X, Luo J, Mei T. Gaussian temporal awareness networks for action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2019, p. 344\u201353.","DOI":"10.1109\/CVPR.2019.00043"},{"key":"10560_CR18","doi-asserted-by":"publisher","first-page":"6688","DOI":"10.1109\/TMM.2022.3213478","volume":"25","author":"C Ju","year":"2022","unstructured":"Ju C, Zhao P, Chen S, Zhang Y, Zhang X, Wang Y, et al. Adaptive mutual supervision for weakly-supervised temporal action localization. IEEE Trans Multimed. 2022;25:6688\u2013701.","journal-title":"IEEE Trans Multimed"},{"key":"10560_CR19","doi-asserted-by":"crossref","unstructured":"Nguyen P, Liu T, Prasad G, Han B. Weakly supervised action localization by sparse temporal pooling network. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2018, p. 6752\u201361.","DOI":"10.1109\/CVPR.2018.00706"},{"key":"10560_CR20","doi-asserted-by":"crossref","unstructured":"Shi B, Dai Q, Mu Y, Wang J. Weakly-supervised action localization by generative attention modeling. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2020, p. 1009\u201319.","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"10560_CR21","doi-asserted-by":"crossref","unstructured":"Islam A, Long C, Radke R. A hybrid attention mechanism for weakly-supervised temporal action localization. In: Proc AAAI Conf Artif Intell (AAAI); 2021, vol. 35, p. 1637\u201345.","DOI":"10.1609\/aaai.v35i2.16256"},{"key":"10560_CR22","doi-asserted-by":"crossref","unstructured":"Kumar Singh K, Jae Lee Y. Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In: Proc IEEE Int Conf Comput Vis (ICCV); 2017, p. 3524\u201333.","DOI":"10.1109\/ICCV.2017.381"},{"key":"10560_CR23","doi-asserted-by":"crossref","unstructured":"Zhong J-X, Li N, Kong W, Zhang T, Li TH, Li G. Step-by-step erasion, one-by-one collection: a weakly supervised temporal action detector. In: Proc ACM Int Conf Multimed (MM); 2018, p. 35\u201344.","DOI":"10.1145\/3240508.3240511"},{"key":"10560_CR24","doi-asserted-by":"crossref","unstructured":"Paul S, Roy S, Roy-Chowdhury AK. W-talc: Weakly-supervised temporal activity localization and classification. In: Proc Eur Conf Comput Vis (ECCV); 2018, p. 563\u201379.","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"10560_CR25","doi-asserted-by":"crossref","unstructured":"Narayan S, Cholakkal H, Khan FS, Shao L. 3c-net: Category count and center loss for weakly-supervised action localization. In: Proc IEEE\/CVF Int Conf Comput Vis (ICCV); 2019, p. 8679\u201387.","DOI":"10.1109\/ICCV.2019.00877"},{"key":"10560_CR26","doi-asserted-by":"crossref","unstructured":"Zhang C, Cao M, Yang D, Chen J, Zou Y. Cola: Weakly-supervised temporal action localization with snippet contrastive learning. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2021, p. 16010\u20139.","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"10560_CR27","doi-asserted-by":"crossref","unstructured":"Zhai Y, Wang L, Tang W, Zhang Q, Yuan J, Hua G. Two-stream consensus network for weakly-supervised temporal action localization. In: Proc Eur Conf Comput Vis (ECCV); 2020, p. 37\u201354. Springer.","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"10560_CR28","doi-asserted-by":"crossref","unstructured":"Yang W, Zhang T, Yu X, Qi T, Zhang Y, Wu F. Uncertainty guided collaborative training for weakly supervised temporal action detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2021, p. 53\u201363.","DOI":"10.1109\/CVPR46437.2021.00012"},{"key":"10560_CR29","doi-asserted-by":"crossref","unstructured":"Hong F-T, Feng J-C, Xu D, Shan Y, Zheng W-S. Cross-modal consensus network for weakly supervised temporal action localization. In: Proc ACM Int Conf Multimed (MM); 2021, p. 1591\u20139.","DOI":"10.1145\/3474085.3475298"},{"key":"10560_CR30","doi-asserted-by":"crossref","unstructured":"Lim G, Kim H, Kim J, Choi Y. Probabilistic vision-language representation for weakly supervised temporal action localization. In: Proc ACM Int Conf Multimed (MM); 2024, p. 5507\u201316.","DOI":"10.1145\/3664647.3681537"},{"issue":"6","key":"10560_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3702233","volume":"15","author":"S Su","year":"2024","unstructured":"Su S, Zhang Y, Gan M. Proposal semantic relationship graph network for temporal action detection. ACM Trans Intell Syst Technol. 2024;15(6):1\u201324.","journal-title":"ACM Trans Intell Syst Technol"},{"issue":"1","key":"10560_CR32","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/s11227-024-06810-6","volume":"81","author":"H Zhang","year":"2025","unstructured":"Zhang H, Lin H, Wang D, Xu D, Zhou F, Guan L, et al. Tscanet: a two-stream context aggregation network for weakly-supervised temporal action localization. J Supercomput. 2025;81(1):311.","journal-title":"J Supercomput"},{"key":"10560_CR33","doi-asserted-by":"publisher","first-page":"137","DOI":"10.5201\/ipol.2013.26","volume":"2013","author":"JS P\u00e9rez","year":"2013","unstructured":"P\u00e9rez JS, Meinhardt-Llopis E, Facciolo G. Tv-l1 optical flow estimation. Image Process On Line. 2013;2013:137\u201350.","journal-title":"Image Process On Line"},{"key":"10560_CR34","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A. Quo vadis, action recognition? A new model and the kinetics dataset. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2017, p. 6299\u2013308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10560_CR35","doi-asserted-by":"crossref","unstructured":"Liu Z, Wang L, Zhang Q, Gao Z, Niu Z, Zheng N, Hua G. Weakly supervised temporal action localization through contrast based evaluation networks. In: Proc IEEE\/CVF Int Conf Comput Vis (ICCV); 2019, p. 3899\u2013908.","DOI":"10.1109\/ICCV.2019.00400"},{"key":"10560_CR36","doi-asserted-by":"crossref","unstructured":"Idrees H, Zamir AR, Jiang Y-G, Gorban A, Laptev I, Sukthankar R, et al. The thumos challenge on action recognition for videos \u201cin the wild\u201d. Comput Vis Image Underst. 2017;155:1\u201323.","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"10560_CR37","doi-asserted-by":"crossref","unstructured":"Caba Heilbron F, Escorcia V, Ghanem B, Carlos Niebles J. Activitynet: A large-scale video benchmark for human activity understanding. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2015, p. 961\u201370.","DOI":"10.1109\/CVPR.2015.7298698"},{"issue":"5","key":"10560_CR38","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/s00530-024-01445-2","volume":"30","author":"M Liu","year":"2024","unstructured":"Liu M, Li W, Ge F, Gao X. Weakly-supervised temporal action localization using multi-branch attention weighting. Multimedia Syst. 2024;30(5):260.","journal-title":"Multimedia Syst"},{"key":"10560_CR39","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al. Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst. 2019;32."},{"key":"10560_CR40","doi-asserted-by":"crossref","unstructured":"Xu M, Zhao C, Rojas DS, Thabet A, Ghanem B. G-tad: Sub-graph localization for temporal action detection. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2020, p. 10156\u201365.","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"10560_CR41","doi-asserted-by":"crossref","unstructured":"Xia K, Wang L, Zhou S, Zheng N, Tang W. Learning to refactor action and co-occurrence features for temporal action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2022, p. 13884\u201393.","DOI":"10.1109\/CVPR52688.2022.01351"},{"key":"10560_CR42","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Lin D, Van Gool L. Untrimmednets for weakly supervised action recognition and detection. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2017, p. 4325\u201334.","DOI":"10.1109\/CVPR.2017.678"},{"key":"10560_CR43","unstructured":"Qu S, Chen G, Li Z, Zhang L, Lu F, Knoll A. Acm-net: Action context modeling network for weakly-supervised temporal action localization. 2021. arXiv:2104.02967."},{"key":"10560_CR44","doi-asserted-by":"crossref","unstructured":"Gao J, Chen M, Xu C. Fine-grained temporal contrastive learning for weakly-supervised temporal action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2022, p. 19999\u201320009.","DOI":"10.1109\/CVPR52688.2022.01937"},{"key":"10560_CR45","doi-asserted-by":"crossref","unstructured":"Ju C, Zheng K, Liu J, Zhao P, Zhang Y, Chang J, Tian Q, Wang Y. Distilling vision-language pre-training to collaborate with weakly-supervised temporal action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2023, p. 14751\u201362.","DOI":"10.1109\/CVPR52729.2023.01417"},{"key":"10560_CR46","doi-asserted-by":"crossref","unstructured":"Gong G, Wang X, Mu Y, Tian Q. Learning temporal co-attention models for unsupervised video action localization. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR); 2020, p. 9819\u201328.","DOI":"10.1109\/CVPR42600.2020.00984"},{"key":"10560_CR47","doi-asserted-by":"crossref","unstructured":"Luo Z, Guillory D, Shi B, Ke W, Wan F, Darrell T, Xu H. Weakly-supervised action localization with expectation-maximization multi-instance learning. In: Proc Eur Conf Comput Vis (ECCV); 2020, p. 729\u201345. Springer.","DOI":"10.1007\/978-3-030-58526-6_43"},{"key":"10560_CR48","doi-asserted-by":"crossref","unstructured":"Liu Z, Wang L, Zhang Q, Tang W, Yuan J, Zheng N, Hua G. Acsnet: Action-context separation network for weakly supervised temporal action localization. In: Proc AAAI Conf Artif Intell (AAAI); 2021, vol. 35, p. 2233\u201341.","DOI":"10.1609\/aaai.v35i3.16322"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10560-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-026-10560-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10560-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T02:14:48Z","timestamp":1771640088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-026-10560-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10560"],"URL":"https:\/\/doi.org\/10.1007\/s12559-026-10560-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6719748\/v1","asserted-by":"object"}]},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"21 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Written informed consent for publication of this paper was obtained from the Civil Aviation University of China and all authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors consent to the publication of this paper, confirming originality and licensing of all content.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Additional datasets and codes are available from the corresponding author upon reasonable request. Please contact\n                      carole_zhang@vip.163.com\n                      .","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"18"}}