{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:05:26Z","timestamp":1791569126738,"version":"4.3.4"},"reference-count":70,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017668","name":"Anhui Provincial Key Research and Development Plan","doi-asserted-by":"publisher","award":["202304a05020045"],"award-info":[{"award-number":["202304a05020045"]}],"id":[{"id":"10.13039\/501100017668","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176246"],"award-info":[{"award-number":["62176246"]}],"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":["61836008"],"award-info":[{"award-number":["61836008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1016\/j.neunet.2024.106307","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T12:57:18Z","timestamp":1713185838000},"page":"106307","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["Weakly supervised temporal action localization with actionness-guided false positive suppression"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7095-5563","authenticated-orcid":false,"given":"Zhilin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-3731","authenticated-orcid":false,"given":"Zilei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4483-9671","authenticated-orcid":false,"given":"Qinying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2024.106307_b1","doi-asserted-by":"crossref","unstructured":"Alwassel, H., Heilbron, F. C., Escorcia, V., & Ghanem, B. (2018). Diagnosing error in temporal action detectors. In Proceedings of the European conference on computer vision (pp. 256\u2013272).","DOI":"10.1007\/978-3-030-01219-9_16"},{"key":"10.1016\/j.neunet.2024.106307_b2","article-title":"Generalized denoising auto-encoders as generative models","volume":"vol. 26","author":"Bengio","year":"2013"},{"key":"10.1016\/j.neunet.2024.106307_b3","series-title":"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.neunet.2024.106307_b4","series-title":"CVPR","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.neunet.2024.106307_b5","series-title":"CVPR","article-title":"Rethinking the faster r-cnn architecture for temporal action localization","author":"Chao","year":"2018"},{"key":"10.1016\/j.neunet.2024.106307_b6","series-title":"Computer vision\u2013ECCV 2022: 17th European conference, tel aviv, Israel, October 23\u201327, 2022, proceedings, part IV","first-page":"192","article-title":"Dual-evidential learning for weakly-supervised temporal action localization","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2024.106307_b7","series-title":"Computer vision\u2013ECCV 2022: 17th European conference, tel aviv, Israel, October 23\u201327, 2022, proceedings, part XXXIV","first-page":"503","article-title":"TallFormer: Temporal action localization with a long-memory transformer","author":"Cheng","year":"2022"},{"key":"10.1016\/j.neunet.2024.106307_b8","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3287208","article-title":"Semantic and temporal contextual correlation learning for weakly-supervised temporal action localization","author":"Fu","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2024.106307_b9","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, M., & Xu, C. (2022). Fine-grained temporal contrastive learning for weakly-supervised temporal action localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19999\u201320009).","DOI":"10.1109\/CVPR52688.2022.01937"},{"key":"10.1016\/j.neunet.2024.106307_b10","series-title":"2020 IEEE international conference on multimedia and expo","first-page":"1","article-title":"Scale matters: Temporal scale aggregation network for precise action localization in untrimmed videos","author":"Gong","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b11","doi-asserted-by":"crossref","unstructured":"He, B., Yang, X., Kang, L., Cheng, Z., Zhou, X., & Shrivastava, A. (2022). ASM-Loc: action-aware segment modeling for weakly-supervised temporal action localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13925\u201313935).","DOI":"10.1109\/CVPR52688.2022.01355"},{"key":"10.1016\/j.neunet.2024.106307_b12","doi-asserted-by":"crossref","unstructured":"Hong, F.-T., Feng, J.-C., Xu, D., Shan, Y., & Zheng, W.-S. (2021). Cross-modal consensus network for weakly supervised temporal action localization. In Proceedings of the 29th ACM international conference on multimedia (pp. 1591\u20131599).","DOI":"10.1145\/3474085.3475298"},{"key":"10.1016\/j.neunet.2024.106307_b13","article-title":"Learning proposal-aware re-ranking for weakly-supervised temporal action localization","author":"Hu","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b14","series-title":"AAAI","article-title":"Relational prototypical network for weakly supervised temporal action localization","author":"Huang","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b15","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, L., & Li, H. (2021). Foreground-action consistency network for weakly supervised temporal action localization. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8002\u20138011).","DOI":"10.1109\/ICCV48922.2021.00790"},{"key":"10.1016\/j.neunet.2024.106307_b16","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, L., & Li, H. (2022). Weakly supervised temporal action localization via representative snippet knowledge propagation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3272\u20133281).","DOI":"10.1109\/CVPR52688.2022.00327"},{"key":"10.1016\/j.neunet.2024.106307_b17","first-page":"1","article-title":"The THUMOS challenge on action recognition for videos \u201cin the wild\u201d","author":"Idrees","year":"2017","journal-title":"CVIU"},{"key":"10.1016\/j.neunet.2024.106307_b18","first-page":"1637","article-title":"A hybrid attention mechanism for weakly-supervised temporal action localization","volume":"vol. 35","author":"Islam","year":"2021"},{"key":"10.1016\/j.neunet.2024.106307_b19","doi-asserted-by":"crossref","unstructured":"Ji, Y., Jia, X., Lu, H., & Ruan, X. (2021). Weakly-supervised temporal action localization via cross-stream collaborative learning. In Proceedings of the 29th ACM international conference on multimedia (pp. 853\u2013861).","DOI":"10.1145\/3474085.3475261"},{"key":"10.1016\/j.neunet.2024.106307_b20","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"10.1016\/j.neunet.2024.106307_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119618","article-title":"Multi-level alignment for few-shot temporal action localization","author":"Keisham","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2024.106307_b22","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.neunet.2024.106307_b23","series-title":"AAAI","article-title":"Background suppression network for weakly-supervised temporal action localization","author":"Lee","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b24","first-page":"1854","article-title":"Weakly-supervised temporal action localization by uncertainty modeling","volume":"35","author":"Lee","year":"2021"},{"key":"10.1016\/j.neunet.2024.106307_b25","doi-asserted-by":"crossref","unstructured":"Li, G., Cheng, D., Ding, X., Wang, N., Wang, X., & Gao, X. (2023). Boosting Weakly-Supervised Temporal Action Localization with Text Information. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10648\u201310657).","DOI":"10.1109\/CVPR52729.2023.01026"},{"key":"10.1016\/j.neunet.2024.106307_b26","doi-asserted-by":"crossref","unstructured":"Li, Z., Ge, Y., Yu, J., & Chen, Z. (2022). Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization. In Proceedings of the 30th ACM international conference on multimedia (pp. 5371\u20135379).","DOI":"10.1145\/3503161.3548300"},{"issue":"7","key":"10.1016\/j.neunet.2024.106307_b27","doi-asserted-by":"crossref","first-page":"4473","DOI":"10.1109\/TCSVT.2021.3125701","article-title":"Weakly supervised temporal action detection with temporal dependency learning","volume":"32","author":"Li","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b28","first-page":"1513","article-title":"Actionness inconsistency-guided contrastive learning for weakly-supervised temporal action localization","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2024.106307_b29","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, T., Ji, W., Wang, J., & Cheng, L. (2022). Exploring denoised cross-video contrast for weakly-supervised temporal action localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19914\u201319924).","DOI":"10.1109\/CVPR52688.2022.01929"},{"key":"10.1016\/j.neunet.2024.106307_b30","series-title":"ECCV","first-page":"3","article-title":"Bsn: Boundary sensitive network for temporal action proposal generation","author":"Lin","year":"2018"},{"key":"10.1016\/j.neunet.2024.106307_b31","series-title":"CVPR","first-page":"1298","article-title":"Completeness modeling and context separation for weakly supervised temporal action localization","author":"Liu","year":"2019"},{"key":"10.1016\/j.neunet.2024.106307_b32","doi-asserted-by":"crossref","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","article-title":"End-to-end temporal action detection with transformer","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2024.106307_b33","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.ins.2023.02.047","article-title":"APSL: Action-positive separation learning for unsupervised temporal action localization","volume":"630","author":"Liu","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2024.106307_b34","doi-asserted-by":"crossref","unstructured":"Luo, W., Zhang, T., Yang, W., Liu, J., Mei, T., Wu, F., et al. (2021). Action unit memory network for weakly supervised temporal action localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9969\u20139979).","DOI":"10.1109\/CVPR46437.2021.00984"},{"key":"10.1016\/j.neunet.2024.106307_b35","doi-asserted-by":"crossref","unstructured":"Ma, J., Gorti, S. K., Volkovs, M., & Yu, G. (2021). Weakly supervised action selection learning in video. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7587\u20137596).","DOI":"10.1109\/CVPR46437.2021.00750"},{"key":"10.1016\/j.neunet.2024.106307_b36","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, August 23\u201328, 2020, proceedings, part XIV 16","first-page":"283","article-title":"Adversarial background-aware loss for weakly-supervised temporal activity localization","author":"Min","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b37","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2023.3272891","article-title":"Collaborative foreground, background, and action modeling network for weakly supervised temporal action localization","author":"Moniruzzaman","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b38","doi-asserted-by":"crossref","unstructured":"Moniruzzaman, M., Yin, Z., He, Z., Qin, R., & Leu, M. C. (2020). Action completeness modeling with background aware networks for weakly-supervised temporal action localization. In Proceedings of the 28th ACM international conference on multimedia (pp. 2166\u20132174).","DOI":"10.1145\/3394171.3413687"},{"key":"10.1016\/j.neunet.2024.106307_b39","series-title":"Difftad: Temporal action detection with proposal denoising diffusion","author":"Nag","year":"2023"},{"key":"10.1016\/j.neunet.2024.106307_b40","series-title":"CVPR","first-page":"6752","article-title":"Weakly supervised action localization by sparse temporal pooling network","author":"Nguyen","year":"2018"},{"key":"10.1016\/j.neunet.2024.106307_b41","doi-asserted-by":"crossref","unstructured":"Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-supervised semantic segmentation with cross-consistency training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12674\u201312684).","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"10.1016\/j.neunet.2024.106307_b42","series-title":"Acm-net: Action context modeling network for weakly-supervised temporal action localization","author":"Qu","year":"2021"},{"key":"10.1016\/j.neunet.2024.106307_b43","doi-asserted-by":"crossref","unstructured":"Ren, H., Yang, W., Zhang, T., & Zhang, Y. (2023). Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2394\u20132404).","DOI":"10.1109\/CVPR52729.2023.00237"},{"key":"10.1016\/j.neunet.2024.106307_b44","doi-asserted-by":"crossref","unstructured":"Rizve, M. N., Mittal, G., Yu, Y., Hall, M., Sajeev, S., Shah, M., et al. (2023). PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 22992\u201323002).","DOI":"10.1109\/CVPR52729.2023.02202"},{"issue":"3","key":"10.1016\/j.neunet.2024.106307_b45","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/TCSVT.2013.2276700","article-title":"Efficient search and localization of human actions in video databases","volume":"24","author":"Shao","year":"2014","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b46","doi-asserted-by":"crossref","unstructured":"Shi, H., Zhang, X.-Y., Li, C., Gong, L., Li, Y., & Bao, Y. (2022). Dynamic Graph Modeling for Weakly-Supervised Temporal Action Localization. In Proceedings of the 30th ACM international conference on multimedia (pp. 3820\u20133828).","DOI":"10.1145\/3503161.3548077"},{"key":"10.1016\/j.neunet.2024.106307_b47","doi-asserted-by":"crossref","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., & Chang, S.-F. (2018). Autoloc: Weakly-supervised temporal action localization in untrimmed videos. In Proceedings of the European conference on computer vision (pp. 154\u2013171).","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"10.1016\/j.neunet.2024.106307_b48","series-title":"CVPR","article-title":"Temporal action localization in untrimmed videos via multi-stage cnns","author":"Shou","year":"2016"},{"issue":"1","key":"10.1016\/j.neunet.2024.106307_b49","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1109\/TCSVT.2022.3201540","article-title":"Slow motion matters: A slow motion enhanced network for weakly supervised temporal action localization","volume":"33","author":"Sun","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b50","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1016\/j.ins.2022.12.044","article-title":"Towards better utilization of pseudo labels for weakly supervised temporal action localization","volume":"623","author":"Tang","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2024.106307_b51","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on machine learning (pp. 1096\u20131103).","DOI":"10.1145\/1390156.1390294"},{"key":"10.1016\/j.neunet.2024.106307_b52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, Y., & Wang, H. (2023). Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18878\u201318887).","DOI":"10.1109\/CVPR52729.2023.01810"},{"key":"10.1016\/j.neunet.2024.106307_b53","series-title":"CVPR","first-page":"4325","article-title":"Untrimmednets for weakly supervised action recognition and detection","author":"Wang","year":"2017"},{"issue":"4","key":"10.1016\/j.neunet.2024.106307_b54","doi-asserted-by":"crossref","first-page":"2186","DOI":"10.1109\/TCSVT.2021.3089323","article-title":"Exploring sub-action granularity for weakly supervised temporal action localization","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2024.106307_b55","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Zheng, Y., & Pan, P. (2022). Rcl: Recurrent continuous localization for temporal action detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13566\u201313575).","DOI":"10.1109\/CVPR52688.2022.01320"},{"issue":"3","key":"10.1016\/j.neunet.2024.106307_b56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3567827","article-title":"Temporal dropout for weakly supervised action localization","volume":"19","author":"Xie","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.neunet.2024.106307_b57","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D. S., Thabet, A., & Ghanem, B. (2020a). G-tad: Sub-graph localization for temporal action detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10156\u201310165).","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"10.1016\/j.neunet.2024.106307_b58","series-title":"CVPR","article-title":"G-TAD: Sub-graph localization for temporal action detection","author":"Xu","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b59","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 Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2024.106307_b60","first-page":"3090","article-title":"Acgnet: Action complement graph network for weakly-supervised temporal action localization","volume":"vol. 36","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2024.106307_b61","doi-asserted-by":"crossref","unstructured":"Yang, W., Zhang, T., Yu, X., Qi, T., Zhang, Y., & Wu, F. (2021). Uncertainty guided collaborative training for weakly supervised temporal action detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 53\u201363).","DOI":"10.1109\/CVPR46437.2021.00012"},{"key":"10.1016\/j.neunet.2024.106307_b62","series-title":"ICLR","article-title":"Marginalized average attentional network for weakly-supervised learning","author":"Yuan","year":"2019"},{"key":"10.1016\/j.neunet.2024.106307_b63","series-title":"ICCV","first-page":"7093","article-title":"Graph convolutional networks for temporal action localization","author":"Zeng","year":"2019"},{"key":"10.1016\/j.neunet.2024.106307_b64","series-title":"ECCV","article-title":"Two-stream consensus network for weakly-supervised temporal action localization","author":"Zhai","year":"2020"},{"key":"10.1016\/j.neunet.2024.106307_b65","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cao, M., Yang, D., Chen, J., & Zou, Y. (2021). Cola: Weakly-supervised temporal action localization with snippet contrastive learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16010\u201316019).","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"10.1016\/j.neunet.2024.106307_b66","series-title":"Computer vision\u2013ECCV 2022: 17th European conference, tel aviv, Israel, October 23\u201327, 2022, proceedings, Part IV","first-page":"492","article-title":"Actionformer: Localizing moments of actions with transformers","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2024.106307_b67","doi-asserted-by":"crossref","unstructured":"Zhao, C., Thabet, A. K., & Ghanem, B. (2021). Video self-stitching graph network for temporal action localization. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13658\u201313667).","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"10.1016\/j.neunet.2024.106307_b68","series-title":"ICCV","first-page":"2914","article-title":"Temporal action detection with structured segment networks","author":"Zhao","year":"2017"},{"key":"10.1016\/j.neunet.2024.106307_b69","doi-asserted-by":"crossref","unstructured":"Zhou, J., & Wu, Y. (2023). Temporal Feature Enhancement Dilated Convolution Network for Weakly-Supervised Temporal Action Localization. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 6028\u20136037).","DOI":"10.1109\/WACV56688.2023.00597"},{"key":"10.1016\/j.neunet.2024.106307_b70","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, W., Wang, L., Zheng, N., & Hua, G. (2021). Enriching local and global contexts for temporal action localization. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13516\u201313525).","DOI":"10.1109\/ICCV48922.2021.01326"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024002314?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024002314?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:37:44Z","timestamp":1778546264000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608024002314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":70,"alternative-id":["S0893608024002314"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106307","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Weakly supervised temporal action localization with actionness-guided false positive suppression","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2024.106307","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"106307"}}