{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:46:17Z","timestamp":1745343977619,"version":"3.37.3"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T00:00:00Z","timestamp":1679702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T00:00:00Z","timestamp":1679702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Nature Science Foundation of China","award":["62006007"],"award-info":[{"award-number":["62006007"]}]},{"name":"National Innovation 2030 Major S &T Project of China","award":["2020AAA0104203"],"award-info":[{"award-number":["2020AAA0104203"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11063-022-11138-4","type":"journal-article","created":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T05:02:36Z","timestamp":1679720556000},"page":"6269-6288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Separately Guided Context-Aware Network for Weakly Supervised Temporal Action Detection"],"prefix":"10.1007","volume":"55","author":[{"given":"Bairong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2524-6800","authenticated-orcid":false,"given":"Yuesheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,25]]},"reference":[{"key":"11138_CR1","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M (2018) Bsn: Boundary sensitive network for temporal action proposal generation. In: Proceedings of the European conference on computer vision, pp 3\u201319","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"11138_CR2","doi-asserted-by":"crossref","unstructured":"Zeng R, Huang W, Gan C, Tan M, Rong Y, Zhao P, Huang J (2019) Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE international conference on computer vision, pp 7093\u20137102","DOI":"10.1109\/ICCV.2019.00719"},{"key":"11138_CR3","doi-asserted-by":"crossref","unstructured":"Paul S, Roy S, Roy-Chowdhury AK (2018) W-talc: weakly-supervised temporal activity localization and classification. In: Proceedings of the European conference on computer vision, pp 563\u2013579","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"11138_CR4","doi-asserted-by":"crossref","unstructured":"Liu D, Jiang T, Wang Y (2019) Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1298\u20131307","DOI":"10.1109\/CVPR.2019.00139"},{"key":"11138_CR5","doi-asserted-by":"crossref","unstructured":"Shi B, Dai Q, Mu Y, Wang J (2020) Weakly-supervised action localization by generative attention modeling. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1006\u20131016","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"11138_CR6","doi-asserted-by":"crossref","unstructured":"Zhai Y, Wang L, Tang W, Zhang Q, Hua G (2020) Two-stream consensus network for weakly-supervised temporal action localization. In: Proceedings of the European conference on computer vision, pp 37\u201354","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"11138_CR7","doi-asserted-by":"crossref","unstructured":"Min K, Corso JJ (2020) Adversarial background-aware loss for weakly-supervised temporal activity localization. In: Proceedings of the European conference on computer vision, pp 283\u2013299","DOI":"10.1007\/978-3-030-58568-6_17"},{"key":"11138_CR8","doi-asserted-by":"crossref","unstructured":"Islam A, Long C, Radke RJ (2021) A hybrid attention mechanism for weakly-supervised temporal action localization. In: Proceedings of the association for the advancement of artificial intelligence, pp 1637\u20131645","DOI":"10.1609\/aaai.v35i2.16256"},{"key":"11138_CR9","doi-asserted-by":"crossref","unstructured":"Yu TY, Ren Z, Li Y, Yan E, Xu N, Yuan J (2019) Temporal structure mining for weakly supervised action detection. In: Proceedings of the IEEE international conference on computer vision, pp 5521\u20135530","DOI":"10.1109\/ICCV.2019.00562"},{"key":"11138_CR10","doi-asserted-by":"crossref","unstructured":"Lee P, Uh Y, Byun H (2020) Background suppression network for weakly-supervised temporal action localization. In: Proceedings of the association for the advancement of artificial intelligence","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"11138_CR11","doi-asserted-by":"crossref","unstructured":"Rashid M, Kjellstr\u00f6m H, Lee YJ (2020) Action graphs: Weakly-supervised action localization with graph convolution networks. Proceedings of the IEEE winter conference on applications of computer vision, pp 604\u2013613","DOI":"10.1109\/WACV45572.2020.9093404"},{"key":"11138_CR12","doi-asserted-by":"crossref","unstructured":"Nguyen P, Liu T, Prasad G, Han B (2018) Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6752\u20136761","DOI":"10.1109\/CVPR.2018.00706"},{"key":"11138_CR13","doi-asserted-by":"crossref","unstructured":"Nguyen P, Ramanan D, Fowlkes C (2019) Weakly-supervised action localization with background modeling. In: Proceedings of the international conference on computer vision, pp 5501\u20135510","DOI":"10.1109\/ICCV.2019.00560"},{"issue":"1","key":"11138_CR14","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s11063-018-9932-3","volume":"50","author":"H Hu","year":"2019","unstructured":"Hu H, Liao Z, Xiao X (2019) Action recognition using multiple pooling strategies of CNN features. Neural Process Lett 50(1):379\u2013396","journal-title":"Neural Process Lett"},{"issue":"1","key":"11138_CR15","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s11063-019-10091-z","volume":"51","author":"Z Liao","year":"2020","unstructured":"Liao Z, Hu H, Liu Y (2020) Action recognition with multiple relative descriptors of trajectories. Neural Process Lett 51(1):287\u2013302","journal-title":"Neural Process Lett"},{"key":"11138_CR16","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Shou Z (2017) Single shot temporal action detection. In: Proceedings of the ACM international conference on multimedia, pp 988\u2013996","DOI":"10.1145\/3123266.3123343"},{"key":"11138_CR17","doi-asserted-by":"crossref","unstructured":"Long F, Yao T, Qiu Z, Tian X, Luo J, Mei T (2019) Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 344\u2013353","DOI":"10.1109\/CVPR.2019.00043"},{"issue":"3","key":"11138_CR18","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1007\/s11063-020-10349-x","volume":"52","author":"J Wang","year":"2020","unstructured":"Wang J, Hu H (2020) Complementary boundary estimation network for temporal action proposal generation. Neural Process Lett 52(3):2275\u20132295","journal-title":"Neural Process Lett"},{"issue":"4","key":"11138_CR19","doi-asserted-by":"publisher","first-page":"2813","DOI":"10.1007\/s11063-021-10500-2","volume":"53","author":"J Zheng","year":"2021","unstructured":"Zheng J, Chen D, Hu H (2021) Boundary adjusted network based on cosine similarity for temporal action proposal generation. Neural Process Lett 53(4):2813\u20132828","journal-title":"Neural Process Lett"},{"key":"11138_CR20","doi-asserted-by":"crossref","unstructured":"Buch S, Escorcia V, Shen C, Ghanem B, Carlos\u00a0Niebles J (2017) Sst: Single-stream temporal action proposals. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2911\u20132920","DOI":"10.1109\/CVPR.2017.675"},{"key":"11138_CR21","doi-asserted-by":"crossref","unstructured":"Chao Y-W, Vijayanarasimhan S, Seybold B, Ross DA, Deng J, Sukthankar R (2018) Rethinking the faster r-cnn architecture for temporal action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1130\u20131139","DOI":"10.1109\/CVPR.2018.00124"},{"key":"11138_CR22","doi-asserted-by":"crossref","unstructured":"Dai X, Singh B, Zhang G, Davis LS, Qiu\u00a0Chen Y (2017) Temporal context network for activity localization in videos. In: Proceedings of the IEEE international conference on computer vision, pp 5793\u20135802","DOI":"10.1109\/ICCV.2017.610"},{"key":"11138_CR23","doi-asserted-by":"crossref","unstructured":"Gao J, Yang Z, Chen K, Sun C, Nevatia R (2017) Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE international conference on computer vision, pp 3628\u20133636","DOI":"10.1109\/ICCV.2017.392"},{"key":"11138_CR24","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang S-F (2016) Temporal action localization in untrimmed videos via multi-stage cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"11138_CR25","doi-asserted-by":"crossref","unstructured":"Xu H, Das A, Saenko K (2017) R-c3d: Region convolutional 3d network for temporal activity detection. In: Proceedings of the IEEE international conference on computer vision, pp 5783\u20135792","DOI":"10.1109\/ICCV.2017.617"},{"key":"11138_CR26","unstructured":"Xiong Y, Zhao Y, Wang L, Lin D, Tang X (2017) A pursuit of temporal accuracy in general activity detection. Preprint arXiv:1703.02716"},{"key":"11138_CR27","doi-asserted-by":"crossref","unstructured":"Zhao P, Xie L, Ju C, Zhang Y, Wang Y, Tian Q (2020) Bottom-up temporal action localization with mutual regularization. In: Proceedings of the European conference on computer vision, pp 539\u2013555","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"11138_CR28","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S (2019) BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the European conference on computer vision, pp 3888\u20133897","DOI":"10.1109\/ICCV.2019.00399"},{"key":"11138_CR29","doi-asserted-by":"crossref","unstructured":"Ma F, Zhu L, Yang Y, Zha S, Kundu G, Feiszli M, Shou Z (2020) Sf-net: single-frame supervision for temporal action localization. In: Proceedings of the European conference on computer vision, vol 12349, pp 420\u2013437","DOI":"10.1007\/978-3-030-58548-8_25"},{"key":"11138_CR30","doi-asserted-by":"crossref","unstructured":"Lee P, Byun H (2021) Learning action completeness from points for weakly-supervised temporal action localization. In: Proceedings of the international conference on computer vision, pp 13628\u201313637","DOI":"10.1109\/ICCV48922.2021.01339"},{"issue":"11","key":"11138_CR31","doi-asserted-by":"publisher","first-page":"8479","DOI":"10.1007\/s00521-022-07102-x","volume":"34","author":"AM Baraka","year":"2022","unstructured":"Baraka AM, Mohd Halim MN (2022) Weakly-supervised temporal action localization: a survey. Neural Comput Appl 34(11):8479\u20138499","journal-title":"Neural Comput Appl"},{"key":"11138_CR32","doi-asserted-by":"crossref","unstructured":"Huang L, Huang Y, Ouyang W, Wang L (2020) Relational prototypical network for weakly supervised temporal action localization. In: Proceedings of the association for the advancement of artificial intelligence, vol 34, pp 11053\u201311060","DOI":"10.1609\/aaai.v34i07.6760"},{"key":"11138_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107686","volume":"110","author":"Y Ge","year":"2021","unstructured":"Ge Y, Qin X, Yang D, J\u00e4gersand M (2021) Deep snippet selective network for weakly supervised temporal action localization. Pattern Recognit 110:107686","journal-title":"Pattern Recognit"},{"key":"11138_CR34","doi-asserted-by":"crossref","unstructured":"Liu Y, Chen J, Chen Z, Deng B, Huang J, Zhang H (2021) The blessings of unlabeled background in untrimmed videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6176\u20136185","DOI":"10.1109\/CVPR46437.2021.00611"},{"key":"11138_CR35","doi-asserted-by":"crossref","unstructured":"Ma J, Gorti SK, Volkovs M, Yu GW (2021) Weakly supervised action selection learning in video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7587\u20137596","DOI":"10.1109\/CVPR46437.2021.00750"},{"key":"11138_CR36","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.neucom.2021.02.086","volume":"443","author":"B Wang","year":"2021","unstructured":"Wang B, Zhao Y, Zhang Y (2021) Pfwnet: pretraining neural network via feature jigsaw puzzle for weakly-supervised temporal action localization. Neurocomputing 443:162\u2013173","journal-title":"Neurocomputing"},{"key":"11138_CR37","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 international conference on computer vision","DOI":"10.1109\/ICCV48922.2021.00790"},{"key":"11138_CR38","doi-asserted-by":"crossref","unstructured":"Lee P, Wang J, Lu Y, Byun H (2021) Weakly-supervised temporal action localization by uncertainty modeling. In: Proceedings of the association for the advancement of artificial intelligence, pp 1854\u20131862","DOI":"10.1609\/aaai.v35i3.16280"},{"key":"11138_CR39","doi-asserted-by":"crossref","unstructured":"Moniruzzaman M, Yin Z, He Z, Qin R, Leu MC (2020) Action completeness modeling with background aware networks for weakly-supervised temporal action localization. In: Proceedings of the ACM international conference on multimedia, pp 2166\u20132174","DOI":"10.1145\/3394171.3413687"},{"key":"11138_CR40","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 conference on computer vision and pattern recognition, pp 16010\u201316019","DOI":"10.1109\/CVPR46437.2021.01575"},{"issue":"9","key":"11138_CR41","first-page":"5886","volume":"44","author":"Z Liu","year":"2022","unstructured":"Liu Z, Wang L, Zhang Q, Tang W, Zheng N, Hua G (2022) Weakly supervised temporal action localization through contrast based evaluation networks. IEEE Trans Pattern Anal Mach Intell 44(9):5886\u20135902","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11138_CR42","doi-asserted-by":"crossref","unstructured":"Zhao T, Han J, Yang L, Zhang D (2022) Equivalent classification mapping for weakly supervised temporal action localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1\u20131","DOI":"10.1109\/TPAMI.2022.3178957"},{"key":"11138_CR43","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1109\/TMM.2021.3073235","volume":"24","author":"Y Zhai","year":"2022","unstructured":"Zhai Y, Wang L, Tang W, Zhang Q, Zheng N, Hua G (2022) Action coherence network for weakly-supervised temporal action localization. IEEE Trans Multimed 24:1857\u20131870","journal-title":"IEEE Trans Multimed"},{"key":"11138_CR44","unstructured":"Yuan Y, Lyu Y, Shen X, Tsang I, Yeung D-Y (2019) Marginalized average attentional network for weakly-supervised learning. In: Proceedings of the international conference on learning representations"},{"key":"11138_CR45","doi-asserted-by":"crossref","unstructured":"Luo W, Zhang T, Yang W, Liu J, Mei T, Wu F, Zhang Y (2021) Action unit memory network for weakly supervised temporal action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9969\u20139979","DOI":"10.1109\/CVPR46437.2021.00984"},{"key":"11138_CR46","doi-asserted-by":"crossref","unstructured":"Narayan S, Cholakkal H, Hayat M, Khan FS, Yang M, Shao L (2021) D2-net: weakly-supervised action localization via discriminative embeddings and denoised activations. In: Proceedings of the IEEE international conference on computer vision","DOI":"10.1109\/ICCV48922.2021.01335"},{"key":"11138_CR47","doi-asserted-by":"crossref","unstructured":"Yang W, Zhang T, Yu X, Tian Q, Zhang Y, Wu F (2021) Uncertainty guided collaborative training for weakly supervised temporal action detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR46437.2021.00012"},{"key":"11138_CR48","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1109\/TIP.2021.3137649","volume":"31","author":"L Huang","year":"2022","unstructured":"Huang L, Wang L, Li H (2022) Multi-modality self-distillation for weakly supervised temporal action localization. IEEE Trans Image Process 31:1504\u20131519","journal-title":"IEEE Trans Image Process"},{"key":"11138_CR49","doi-asserted-by":"crossref","unstructured":"Hong F, Feng J, Xu D, Shan Y, Zheng W (2021) Cross-modal consensus network for weakly supervised temporal action localization. In: Proceedings of the ACM international conference on multimedia, pp 1591\u20131599","DOI":"10.1145\/3474085.3475298"},{"key":"11138_CR50","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the international conference on learning representations"},{"key":"11138_CR51","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the association for the advancement of artificial intelligence, pp 7444\u20137452","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"11138_CR52","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s11063-021-10622-7","volume":"54","author":"M Zhang","year":"2021","unstructured":"Zhang M, Hu H, Li Z, Chen J (2021) Proposal-based graph attention networks for workflow detection. Neural Process Lett 54:101\u2013123","journal-title":"Neural Process Lett"},{"key":"11138_CR53","doi-asserted-by":"crossref","unstructured":"Xu M, Zhao C, Rojas DS, Thabet A, Ghanem B (2020) G-tad: sub-graph localization for temporal action detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10153\u201310162","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"11138_CR54","doi-asserted-by":"crossref","unstructured":"Li J, Liu X, Zong Z, Zhao W, Zhang M, Song J (2020) Graph attention based proposal 3d convnets for action detection. In: Proceedings of the association for the advancement of artificial intelligence, pp 4626\u20134633","DOI":"10.1609\/aaai.v34i04.5893"},{"key":"11138_CR55","doi-asserted-by":"crossref","unstructured":"Bai Y, Wang Y, Tong Y, Yang Y, Liu Q, Liu J (2020) Boundary content graph neural network for temporal action proposal generation. In: Proceedings of the European conference on computer vision, vol 12373, pp 121\u2013137","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"11138_CR56","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"11138_CR57","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.243"},{"key":"11138_CR58","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Lin D, Van\u00a0Gool L (2017) Untrimmednets for weakly supervised action recognition and detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4325\u20134334","DOI":"10.1109\/CVPR.2017.678"},{"key":"11138_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees H, Zamir AR, Jiang Y-G, Gorban A, Laptev I, Sukthankar R, Shah M (2017) The thumos challenge on action recognition for videos \u201cin the wild\u2019\u2019. Comput Vis Image Underst 155:1\u201323","journal-title":"Comput Vis Image Underst"},{"key":"11138_CR60","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron F, Escorcia V, Ghanem B, Carlos\u00a0Niebles J (2015) Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"11138_CR61","doi-asserted-by":"crossref","unstructured":"Xu Y, Zhang C, Cheng Z, Xie J, Niu Y, Pu S, Wu F (2019) Segregated temporal assembly recurrent networks for weakly supervised multiple action detection. In: Proceedings of the association for the advancement of artificial intelligence, pp 9070\u20139078","DOI":"10.1609\/aaai.v33i01.33019070"},{"key":"11138_CR62","doi-asserted-by":"crossref","unstructured":"Zhang C, Xu Y, Cheng Z, Niu Y, Pu S, Wu F, Zou F (2019) Adversarial seeded sequence growing for weakly-supervised temporal action localization. In: Proceedings of the ACM international conference on multimedia, pp 738\u2013746","DOI":"10.1145\/3343031.3351044"},{"key":"11138_CR63","doi-asserted-by":"crossref","unstructured":"Narayan S, Cholakkal H, Khan FS, Shao L (2019) 3c-net: category count and center loss for weakly-supervised action localization. In: Proceedings of the IEEE international conference on computer vision, pp 8678\u20138686","DOI":"10.1109\/ICCV.2019.00877"},{"key":"11138_CR64","doi-asserted-by":"crossref","unstructured":"Zhang XY, Shi H, Li C, Li P (2020) Multi-instance multi-label action recognition and localization based on spatio-temporal pre-trimming for untrimmed videos. In: Proceedings of the association for the advancement of artificial intelligence, vol 34, pp 12886\u201312893","DOI":"10.1609\/aaai.v34i07.6986"},{"key":"11138_CR65","doi-asserted-by":"crossref","unstructured":"Jain M, Ghodrati A, Snoek CGM (2020) Actionbytes: learning from trimmed videos to localize actions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1168\u20131177","DOI":"10.1109\/CVPR42600.2020.00125"},{"key":"11138_CR66","doi-asserted-by":"crossref","unstructured":"Gong G, Wang X, Mu Y, Tian Q (2020) Learning temporal co-attention models for unsupervised video action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9816\u20139825","DOI":"10.1109\/CVPR42600.2020.00984"},{"key":"11138_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107831","volume":"113","author":"X Zhang","year":"2021","unstructured":"Zhang X, Shi H, Li C, Li P, Li Z, Ren P (2021) Weakly-supervised action localization via embedding-modeling iterative optimization. Pattern Recognit 113:107831","journal-title":"Pattern Recognit"},{"key":"11138_CR68","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of advances in neural information processing systems, pp 5998\u20136008"},{"issue":"8","key":"11138_CR69","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11138-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-11138-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11138-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T16:28:10Z","timestamp":1696004890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-11138-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,25]]},"references-count":69,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["11138"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-11138-4","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2023,3,25]]},"assertion":[{"value":"15 December 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}