{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:30:43Z","timestamp":1781299843817,"version":"3.54.1"},"reference-count":205,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Funding of Special Development Project of Tianchang Intelligent Equipment and Instrument Research Institute","award":["tzy202221"],"award-info":[{"award-number":["tzy202221"]}]},{"name":"Funding of Special Development Project of Tianchang Intelligent Equipment and Instrument Research Institute","award":["tzy202221"],"award-info":[{"award-number":["tzy202221"]}]},{"name":"Funding of Special Development Project of Tianchang Intelligent Equipment and Instrument Research Institute","award":["tzy202221"],"award-info":[{"award-number":["tzy202221"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876079"],"award-info":[{"award-number":["61876079"]}],"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":["61876079"],"award-info":[{"award-number":["61876079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Temporal Action Detection (TAD) aims to accurately capture each action interval in an untrimmed video and to understand human actions. This paper comprehensively surveys the state-of-the-art techniques and models used for TAD task. Firstly, it conducts comprehensive research on this field through Citespace and comprehensively introduce relevant dataset. Secondly, it summarizes three types of methods, i.e., anchor-based, boundary-based, and query-based, from the design method level. Thirdly, it summarizes three types of supervised learning methods from the level of learning methods, i.e., fully supervised, weakly supervised, and unsupervised. Finally, this paper explores the current problems, and proposes prospects in TAD task.<\/jats:p>","DOI":"10.1007\/s10462-023-10650-w","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:02:12Z","timestamp":1706810532000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Overview of temporal action detection based on deep learning"],"prefix":"10.1007","volume":"57","author":[{"given":"Kai","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaowen","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keer","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingfeng","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxue","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,1]]},"reference":[{"key":"10650_CR1","doi-asserted-by":"crossref","unstructured":"Abdelgwad M (2021) Arabic aspect based sentiment classification using bert. arXiv: 2107.13290","DOI":"10.1186\/s40537-022-00656-6"},{"key":"10650_CR2","unstructured":"Abu-El-Haija S, Kothari N, Lee J, et\u00a0al (2016) Youtube-8m: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675"},{"issue":"8","key":"10650_CR3","doi-asserted-by":"publisher","first-page":"5789","DOI":"10.1007\/s10462-021-09958-2","volume":"54","author":"FA Acheampong","year":"2021","unstructured":"Acheampong FA, Nunoo-Mensah H, Chen W (2021) Transformer models for text-based emotion detection: a review of bert-based approaches. Artif Int Rev 54(8):5789\u20135829","journal-title":"Artif Int Rev"},{"key":"10650_CR4","first-page":"9758","volume":"33","author":"H Alwassel","year":"2020","unstructured":"Alwassel H, Mahajan D, Korbar B et al (2020) Self-supervised learning by cross-modal audio-video clustering. Adv Neural Inf Process Syst 33:9758\u20139770","journal-title":"Adv Neural Inf Process Syst"},{"key":"10650_CR5","doi-asserted-by":"crossref","unstructured":"Alwassel H, Giancola S, Ghanem B (2021) Tsp: temporally-sensitive pretraining of video encoders for localization tasks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3173\u20133183","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"10650_CR6","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, et\u00a0al (2021) Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10650_CR7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.0473","author":"D Bahdanau","year":"2014","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. Comput Sci. https:\/\/doi.org\/10.48550\/arXiv.1409.0473","journal-title":"Comput Sci"},{"key":"10650_CR8","doi-asserted-by":"crossref","unstructured":"Bai Y, Wang Y, Tong Y, et\u00a0al (2020) Boundary content graph neural network for temporal action proposal generation. In: European conference on computer vision, pp 121\u2013137. Springer","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"10650_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00521-022-07102-x","volume":"34","author":"A Baraka","year":"2022","unstructured":"Baraka A, Mohd Noor MH (2022) Weakly-supervised temporal action localization: a survey. Neural Comput Appl 34:1\u201321","journal-title":"Neural Comput Appl"},{"key":"10650_CR10","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? In: ICML, p 4"},{"key":"10650_CR11","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, et\u00a0al (2017) Soft-nms\u2013improving object detection with one line of code. In: Proceedings of the IEEE international conference on computer vision, pp 5561\u20135569","DOI":"10.1109\/ICCV.2017.593"},{"key":"10650_CR12","unstructured":"Buch S, Escorcia V, Ghanem B, et al (2019) End-to-end, single-stream temporal action detection in untrimmed videos.  In: Proceedings of the British Machine Vision Conference (2019)"},{"key":"10650_CR13","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron F, Escorcia V, Ghanem B, et\u00a0al (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":"10650_CR14","doi-asserted-by":"publisher","first-page":"5203","DOI":"10.1109\/TIP.2022.3193752","volume":"31","author":"M Cao","year":"2022","unstructured":"Cao M, Zhang C, Chen L et al (2022) Deep motion prior for weakly-supervised temporal action localization. IEEE Trans Image Process 31:5203\u20135213","journal-title":"IEEE Trans Image Process"},{"key":"10650_CR15","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et\u00a0al (2020) End-to-end object detection with transformers. In: European conference on computer vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10650_CR16","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":"10650_CR17","doi-asserted-by":"crossref","unstructured":"Chao YW, Vijayanarasimhan S, Seybold B, et\u00a0al (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":"10650_CR18","doi-asserted-by":"publisher","first-page":"5303","DOI":"10.1073\/pnas.0307513100","volume":"101","author":"C Chen","year":"2004","unstructured":"Chen C (2004) Searching for intellectual turning points: progressive knowledge domain visualization. Proc Natl Acad Sci 101:5303\u20135310","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"10650_CR19","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1002\/asi.20317","volume":"57","author":"C Chen","year":"2006","unstructured":"Chen C (2006) Citespace ii: detecting and visualizing emerging trends and transient patterns in scientific literature. J Am Soc Inf Sci Technol 57(3):359\u2013377","journal-title":"J Am Soc Inf Sci Technol"},{"key":"10650_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5128-9","volume-title":"Mapping scientific frontiers: the quest for knowledge visualization","author":"C Chen","year":"2013","unstructured":"Chen C (2013) Mapping scientific frontiers: the quest for knowledge visualization. Springer, Berlin"},{"issue":"104","key":"10650_CR21","first-page":"144","volume":"109","author":"Y Chen","year":"2021","unstructured":"Chen Y, Guo B, Shen Y et al (2021) Boundary graph convolutional network for temporal action detection. Image Vis Comput 109(104):144","journal-title":"Image Vis Comput"},{"issue":"7","key":"10650_CR22","doi-asserted-by":"publisher","first-page":"1386","DOI":"10.1002\/asi.21309","volume":"61","author":"C Chen","year":"2010","unstructured":"Chen C, Ibekwe-SanJuan F, Hou J (2010) The structure and dynamics of Cocitation clusters: a multiple-perspective cocitation analysis. J Am Soc Inf Sci Technol 61(7):1386\u20131409","journal-title":"J Am Soc Inf Sci Technol"},{"key":"10650_CR23","doi-asserted-by":"crossref","unstructured":"Chen J, Ho CM (2022) Mm-vit: Multi-modal video transformer for compressed video action recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1910\u20131921","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"10650_CR24","unstructured":"Chen T, Kornblith S, Norouzi M, et\u00a0al (2020a) A simple framework for contrastive learning of visual representations. In: International conference on machine learning, PMLR, pp 1597\u20131607"},{"key":"10650_CR25","unstructured":"Chen X, Fan H, Girshick R, et\u00a0al (2020b) Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"10650_CR26","doi-asserted-by":"crossref","unstructured":"Corona K, Osterdahl K, Collins R, et\u00a0al (2021) Meva: A large-scale multiview, multimodal video dataset for activity detection. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1060\u20131068","DOI":"10.1109\/WACV48630.2021.00110"},{"key":"10650_CR27","doi-asserted-by":"crossref","unstructured":"Dai Z, Yang Z, Yang Y, et\u00a0al (2019) Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860","DOI":"10.18653\/v1\/P19-1285"},{"issue":"1","key":"10650_CR28","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1113\/jphysiol.1984.sp015498","volume":"357","author":"A Derrington","year":"1984","unstructured":"Derrington A, Lennie P (1984) Spatial and temporal contrast sensitivities of Neurones in lateral geniculate nucleus of macaque. J Physiol 357(1):219\u2013240","journal-title":"J Physiol"},{"key":"10650_CR29","unstructured":"Devlin J, Chang MW, Lee K, et\u00a0al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"10650_CR30","unstructured":"Diba A, Fayyaz M, Sharma V, et\u00a0al (2017) Temporal 3d convnets: new architecture and transfer learning for video classification. arXiv preprint arXiv:1711.08200"},{"key":"10650_CR31","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne\u00a0Hendricks L, Guadarrama S, et\u00a0al (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10650_CR32","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et\u00a0al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"10650_CR33","doi-asserted-by":"crossref","unstructured":"Escorcia V, Caba\u00a0Heilbron F, Niebles JC, et\u00a0al (2016) Daps: Deep action proposals for action understanding. In: European conference on computer vision, Springer, pp 768\u2013784","DOI":"10.1007\/978-3-319-46487-9_47"},{"issue":"1","key":"10650_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0896-6273(94)90455-3","volume":"13","author":"DC Van Essen","year":"1994","unstructured":"Van Essen DC, Gallant JL (1994) Neural mechanisms of form and motion processing in the primate visual system. Neuron 13(1):1\u201310","journal-title":"Neuron"},{"key":"10650_CR35","doi-asserted-by":"crossref","unstructured":"Fan H, Xiong B, Mangalam K, et\u00a0al (2021) Multiscale vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6824\u20136835","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"10650_CR36","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4768\u20134777","DOI":"10.1109\/CVPR.2017.787"},{"key":"10650_CR37","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, et\u00a0al (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6202\u20136211","DOI":"10.1109\/ICCV.2019.00630"},{"issue":"1","key":"10650_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/cercor\/1.1.1","volume":"1","author":"DJ Van Felleman","year":"1991","unstructured":"Felleman DJ, Van\u00a0Essen DC (1991) Distributed hierarchical processing in the primate cerebral cortex. Cerebral cortex  1(1):1\u201347","journal-title":"Cerebral cortex"},{"key":"10650_CR39","doi-asserted-by":"crossref","unstructured":"Gao J, Yang Z, Chen K, et\u00a0al (2017a) 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":"10650_CR40","doi-asserted-by":"crossref","unstructured":"Gao J, Yang Z, Nevatia R (2017b) Cascaded boundary regression for temporal action detection. arXiv preprint arXiv:1705.01180","DOI":"10.5244\/C.31.52"},{"key":"10650_CR41","doi-asserted-by":"crossref","unstructured":"Gao J, Shi Z, Wang G, et\u00a0al (2020) Accurate temporal action proposal generation with relation-aware pyramid network. In: Proceedings of the AAAI conference on artificial intelligence, pp 10,810\u201310,817","DOI":"10.1609\/aaai.v34i07.6711"},{"key":"10650_CR42","doi-asserted-by":"crossref","unstructured":"Garg S, Vu T, Moschitti A (2020) Tanda: transfer and adapt pre-trained transformer models for answer sentence selection. In: Proceedings of the AAAI conference on artificial intelligence, pp 7780\u20137788","DOI":"10.1609\/aaai.v34i05.6282"},{"key":"10650_CR43","unstructured":"Ghanem B, Niebles JC, Snoek C, et\u00a0al (2017) Activitynet challenge 2017 summary. arXiv preprint arXiv:1710.08011"},{"key":"10650_CR44","doi-asserted-by":"crossref","unstructured":"Ghorbani S, Mahdaviani K, Thaler A, et\u00a0al (2020) Movi: a large multipurpose motion and video dataset. arXiv preprint arXiv:2003.01888","DOI":"10.1371\/journal.pone.0253157"},{"key":"10650_CR45","doi-asserted-by":"crossref","unstructured":"Girdhar R, Carreira J, Doersch C, et\u00a0al (2019) Video action transformer network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 244\u2013253","DOI":"10.1109\/CVPR.2019.00033"},{"key":"10650_CR46","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, et\u00a0al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"10650_CR47","doi-asserted-by":"crossref","unstructured":"Gong G, Wang X, Mu Y, et\u00a0al (2020a) Learning temporal co-attention models for unsupervised video action localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9819\u20139828","DOI":"10.1109\/CVPR42600.2020.00984"},{"key":"10650_CR48","doi-asserted-by":"crossref","unstructured":"Gong G, Zheng L, Mu Y (2020b) Scale matters: Temporal scale aggregation network for precise action localization in untrimmed videos. In: 2020 IEEE international conference on multimedia and expo (ICME), IEEE, pp 1\u20136","DOI":"10.1109\/ICME46284.2020.9102850"},{"issue":"12","key":"10650_CR49","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick L, Blank M, Shechtman E et al (2007) Actions as space-time shapes. IEEE Trans Pattern Anal Mach Intell 29(12):2247\u20132253","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR50","first-page":"1","volume":"56","author":"M Graziani","year":"2022","unstructured":"Graziani M, Dutkiewicz L, Calvaresi D et al (2022) A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences. Artif Intell Rev 56:1\u201332","journal-title":"Artif Intell Rev"},{"key":"10650_CR51","first-page":"21,271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill JB, Strub F, Altch\u00e9 F et al (2020) Bootstrap your own latent-a new approach to self-supervised learning. Adv Neural Inf Process Syst 33:21,271-21,284","journal-title":"Adv Neural Inf Process Syst"},{"key":"10650_CR52","doi-asserted-by":"crossref","unstructured":"Gu C, Sun C, Ross DA, et\u00a0al (2018) Ava: A video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6047\u20136056","DOI":"10.1109\/CVPR.2018.00633"},{"key":"10650_CR53","doi-asserted-by":"crossref","unstructured":"Guo H, Wang H, Ji Q (2022) Uncertainty-guided probabilistic transformer for complex action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 20,052\u201320,061","DOI":"10.1109\/CVPR52688.2022.01942"},{"key":"10650_CR54","unstructured":"Gutmann M, Hyv\u00e4rinen A (2010) Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings, pp 297\u2013304"},{"key":"10650_CR55","first-page":"5679","volume":"33","author":"T Han","year":"2020","unstructured":"Han T, Xie W, Zisserman A (2020) Self-supervised co-training for video representation learning. Adv Neural Inf Process Syst 33:5679\u20135690","journal-title":"Adv Neural Inf Process Syst"},{"key":"10650_CR56","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, et\u00a0al (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10650_CR57","doi-asserted-by":"crossref","unstructured":"Heilbron FC, Niebles JC, Ghanem B (2016) Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1914\u20131923","DOI":"10.1109\/CVPR.2016.211"},{"key":"10650_CR58","unstructured":"Horn G, Perona P (2017) The devil is in the tails: fine-grained classification in the wild. arXiv preprint arXiv:1709.01450 2"},{"key":"10650_CR59","doi-asserted-by":"crossref","unstructured":"Hsieh HY, Chen DJ, Liu TL (2022) Contextual proposal network for action localization. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2129\u20132138","DOI":"10.1109\/WACV51458.2022.00084"},{"issue":"3","key":"10650_CR60","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.3390\/app12031028","volume":"12","author":"K Hu","year":"2022","unstructured":"Hu K, Ding Y, Jin J et al (2022) Skeleton motion recognition based on multi-scale deep Spatio-temporal features. Appl Sci 12(3):1028","journal-title":"Appl Sci"},{"issue":"14","key":"10650_CR61","doi-asserted-by":"publisher","first-page":"5259","DOI":"10.3390\/s22145259","volume":"22","author":"K Hu","year":"2022","unstructured":"Hu K, Ding Y, Jin J et al (2022) Multiple attention mechanism graph convolution HAR model based on coordination theory. Sensors 22(14):5259","journal-title":"Sensors"},{"key":"10650_CR62","first-page":"1","volume":"56","author":"K Hu","year":"2022","unstructured":"Hu K, Jin J, Zheng F et al (2022) Overview of behavior recognition based on deep learning. Artif Intell Rev 56:1\u201333","journal-title":"Artif Intell Rev"},{"issue":"106","key":"10650_CR63","first-page":"196","volume":"123","author":"K Hu","year":"2023","unstructured":"Hu K, Weng C, Shen C et al (2023) A multi-stage underwater image aesthetic enhancement algorithm based on a generative adversarial network. Eng Appl Artif Intell 123(106):196","journal-title":"Eng Appl Artif Intell"},{"issue":"17","key":"10650_CR64","doi-asserted-by":"publisher","first-page":"7876","DOI":"10.3390\/app11177876","volume":"11","author":"K Hu","year":"2021","unstructured":"Hu K, Zheng F, Weng L et al (2021) Action recognition algorithm of Spatio-temporal differential LSTM based on feature enhancement. Appl Sci 11(17):7876","journal-title":"Appl Sci"},{"key":"10650_CR65","doi-asserted-by":"crossref","unstructured":"Huang L, Huang Y, Ouyang W, et\u00a0al (2020) Relational prototypical network for weakly supervised temporal action localization. In: proceedings of the AAAI conference on artificial intelligence, pp 11,053\u201311,060","DOI":"10.1609\/aaai.v34i07.6760"},{"key":"10650_CR66","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"},{"issue":"2","key":"10650_CR67","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1152\/jn.1965.28.2.229","volume":"28","author":"DH Hubel","year":"1965","unstructured":"Hubel DH, Wiesel TN (1965) Receptive fields and functional architecture in two Nonstriate visual areas (18 and 19) of the cat. J Neurophys 28(2):229\u2013289","journal-title":"J Neurophys"},{"key":"10650_CR68","doi-asserted-by":"publisher","first-page":"134611","DOI":"10.1109\/ACCESS.2021.3115476","volume":"9","author":"MS Hutchinson","year":"2021","unstructured":"Hutchinson MS, Gadepally VN (2021) Video action understanding: a tutorial. IEEE Access 9:134611\u2013134637","journal-title":"IEEE Access"},{"key":"10650_CR69","doi-asserted-by":"crossref","unstructured":"Islam A, Long C, Radke R (2021) A hybrid attention mechanism for weakly-supervised temporal action localization. In: Proceedings of the AAAI conference on artificial intelligence, pp 1637\u20131645","DOI":"10.1609\/aaai.v35i2.16256"},{"key":"10650_CR70","doi-asserted-by":"crossref","unstructured":"Jenni S, Jin H (2021) Time-equivariant contrastive video representation learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9970\u20139980","DOI":"10.1109\/ICCV48922.2021.00982"},{"key":"10650_CR71","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, et\u00a0al (2014) Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"10650_CR72","unstructured":"Jiang YG, Liu J, Roshan\u00a0Zamir A, et\u00a0al (2014) THUMOS challenge: action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"10650_CR73","doi-asserted-by":"crossref","unstructured":"Ke Y, Sukthankar R, Hebert M (2007) Event detection in crowded videos. In: 2007 IEEE 11th international conference on computer vision, IEEE, pp 1\u20138","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"10650_CR74","doi-asserted-by":"crossref","unstructured":"Klaser A, Marsza\u0142ek M, Schmid C (2008) A spatio-temporal descriptor based on 3d-gradients. In: BMVC 2008-19th British machine vision conference, British Machine Vision Association, pp 275\u20131","DOI":"10.5244\/C.22.99"},{"issue":"5","key":"10650_CR75","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong Y, Fu Y (2022) Human action recognition and prediction: a survey. Int J Comput Vis 130(5):1366\u20131401","journal-title":"Int J Comput Vis"},{"issue":"3","key":"10650_CR76","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10462-007-9052-3","volume":"26","author":"SB Kotsiantis","year":"2006","unstructured":"Kotsiantis SB, Zaharakis ID, Pintelas PE (2006) Machine learning: a review of classification and combining techniques. Artif Intell Rev 26(3):159\u2013190","journal-title":"Artif Intell Rev"},{"issue":"6","key":"10650_CR77","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"10650_CR78","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, et\u00a0al (2011) Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision, IEEE, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"10650_CR79","doi-asserted-by":"crossref","unstructured":"Kumar S, Garg S, Mehta K, et\u00a0al (2019) Improving answer selection and answer triggering using hard negatives. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 5911\u20135917","DOI":"10.18653\/v1\/D19-1604"},{"key":"10650_CR80","doi-asserted-by":"crossref","unstructured":"Kumar\u00a0Singh K, Jae\u00a0Lee Y (2017) Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In: Proceedings of the IEEE international conference on computer vision, pp 3524\u20133533","DOI":"10.1109\/ICCV.2017.381"},{"key":"10650_CR81","unstructured":"Lan Z, Chen M, Goodman S, et\u00a0al (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942"},{"issue":"2","key":"10650_CR82","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I (2005) On space-time interest points. Int J Comput Vis 64(2):107\u2013123","journal-title":"Int J Comput Vis"},{"key":"10650_CR83","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/j.neucom.2021.05.103","volume":"470","author":"I Lauriola","year":"2022","unstructured":"Lauriola I, Lavelli A, Aiolli F (2022) An introduction to deep learning in natural language processing: models, techniques, and tools. Neurocomputing 470:443\u2013456","journal-title":"Neurocomputing"},{"key":"10650_CR84","first-page":"1","volume":"55","author":"N Le","year":"2021","unstructured":"Le N, Rathour VS, Yamazaki K et al (2021) Deep reinforcement learning in computer vision: a comprehensive survey. Artif Intell Rev 55:1\u201387","journal-title":"Artif Intell Rev"},{"issue":"4","key":"10650_CR85","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S et al (2020) Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4):1234\u20131240","journal-title":"Bioinformatics"},{"key":"10650_CR86","unstructured":"Lee P, Uh Y, Byun H (2020b) Background suppression network for weakly-supervised temporal action localization. In: Proceedings of the AAAI conference on artificial intelligence, pp 11,320\u201311,327"},{"key":"10650_CR87","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li Z, Gavrilyuk K, Gavves E et al (2018) Videolstm convolves, attends and flows for action recognition. Comput Vis Image Understand 166:41\u201350","journal-title":"Comput Vis Image Understand"},{"key":"10650_CR88","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163459","author":"B Li","year":"2022","unstructured":"Li B, Guo B, Zhu Y et al (2022) Superframe-based temporal proposals for weakly supervised temporal action detection. IEEE Trans Multimed. https:\/\/doi.org\/10.1109\/TMM.2022.3163459","journal-title":"IEEE Trans Multimed"},{"issue":"104","key":"10650_CR89","first-page":"669","volume":"110","author":"M Li","year":"2022","unstructured":"Li M, Huang B, Tian G (2022) A comprehensive survey on 3d face recognition methods. Engineering Applications of Artificial Intelligence 110(104):669","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10650_CR90","doi-asserted-by":"crossref","unstructured":"Li W, Hosseini\u00a0Jafari O, Rother C (2018a) Deep object co-segmentation. In: Asian conference on computer vision, Springer, pp 638\u2013653","DOI":"10.1007\/978-3-030-20893-6_40"},{"key":"10650_CR91","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, et\u00a0al (2019) Selective kernel networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"key":"10650_CR92","doi-asserted-by":"crossref","unstructured":"Li Y, Lin W, See J, et\u00a0al (2020) Cfad: Coarse-to-fine action detector for spatiotemporal action localization. In: European conference on computer vision, Springer, pp 510\u2013527","DOI":"10.1007\/978-3-030-58517-4_30"},{"key":"10650_CR93","doi-asserted-by":"crossref","unstructured":"Lin C, Li J, Wang Y, et\u00a0al (2020) Fast learning of temporal action proposal via dense boundary generator. In: Proceedings of the AAAI conference on artificial intelligence, pp 11,499\u201311,506","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"10650_CR94","doi-asserted-by":"crossref","unstructured":"Lin C, Xu C, Luo D, et\u00a0al (2021) Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3320\u20133329","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"10650_CR95","doi-asserted-by":"crossref","unstructured":"Lin J, Gan C, Han S (2019a) Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7083\u20137093","DOI":"10.1109\/ICCV.2019.00718"},{"key":"10650_CR96","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Shou Z (2017) Single shot temporal action detection. In: Proceedings of the 25th ACM international conference on Multimedia, pp 988\u2013996","DOI":"10.1145\/3123266.3123343"},{"key":"10650_CR97","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, et\u00a0al (2018) Bsn: Boundary sensitive network for temporal action proposal generation. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"10650_CR98","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, et\u00a0al (2019b) Bmn: Boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3889\u20133898","DOI":"10.1109\/ICCV.2019.00399"},{"key":"10650_CR99","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu X, Wang Q, Hu Y et al (2022) End-to-end temporal action detection with transformer. IEEE Trans Image Process 31:5427\u20135441","journal-title":"IEEE Trans Image Process"},{"key":"10650_CR100","doi-asserted-by":"publisher","first-page":"6937","DOI":"10.1109\/TIP.2022.3217368","volume":"31","author":"Y Liu","year":"2022","unstructured":"Liu Y, Wang L, Wang Y et al (2022) Fineaction: a fine-grained video dataset for temporal action localization. IEEE Trans Image Process 31:6937\u20136950","journal-title":"IEEE Trans Image Process"},{"key":"10650_CR101","doi-asserted-by":"crossref","unstructured":"Liu Q, Wang Z (2020) Progressive boundary refinement network for temporal action detection. In: Proceedings of the AAAI conference on artificial intelligence, pp 11,612\u201311,619","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"10650_CR102","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, et\u00a0al (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10650_CR103","unstructured":"Liu Y, Ott M, Goyal N, et\u00a0al (2019b) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"10650_CR104","doi-asserted-by":"crossref","unstructured":"Liu Z, Wang L, Zhang Q, et\u00a0al (2019c) Weakly supervised temporal action localization through contrast based evaluation networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3899\u20133908","DOI":"10.1109\/ICCV.2019.00400"},{"key":"10650_CR105","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et\u00a0al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10,012\u201310,022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10650_CR106","doi-asserted-by":"crossref","unstructured":"Liu D, Jiang T, Wang Y (2019a) Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1298\u20131307","DOI":"10.1109\/CVPR.2019.00139"},{"key":"10650_CR107","doi-asserted-by":"crossref","unstructured":"Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos \u201cin the wild\u201d. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp 1996\u20132003","DOI":"10.1109\/CVPR.2009.5206744"},{"issue":"4853","key":"10650_CR108","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1126\/science.3283936","volume":"240","author":"M Livingstone","year":"1988","unstructured":"Livingstone M, Hubel D (1988) Segregation of form, color, movement, and depth: anatomy, physiology, and perception. Science 240(4853):740\u2013749","journal-title":"Science"},{"key":"10650_CR109","doi-asserted-by":"crossref","unstructured":"Long F, Yao T, Qiu Z, et\u00a0al (2019) Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 344\u2013353","DOI":"10.1109\/CVPR.2019.00043"},{"key":"10650_CR110","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.neucom.2018.10.095","volume":"396","author":"M Majd","year":"2020","unstructured":"Majd M, Safabakhsh R (2020) Correlational convolutional LSTM for human action recognition. Neurocomputing 396:224\u2013229","journal-title":"Neurocomputing"},{"key":"10650_CR111","doi-asserted-by":"crossref","unstructured":"Marszalek M, Laptev I, Schmid C (2009) Actions in context. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp 2929\u20132936","DOI":"10.1109\/CVPRW.2009.5206557"},{"issue":"2","key":"10650_CR112","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2019","unstructured":"Monfort M, Andonian A, Zhou B et al (2019) Moments in time dataset: one million videos for event understanding. IEEE Trans Pattern Anal Mach Intell 42(2):502\u2013508","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR113","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1016\/j.future.2021.06.045","volume":"125","author":"K Muhammad","year":"2021","unstructured":"Muhammad K, Ullah A, Imran AS et al (2021) Human action recognition using attention based LSTM network with dilated CNN features. Future Gener Comput Syst 125:820\u2013830","journal-title":"Future Gener Comput Syst"},{"key":"10650_CR114","doi-asserted-by":"crossref","unstructured":"Narayan S, Cholakkal H, Khan FS, et\u00a0al (2019) 3c-net: Category count and center loss for weakly-supervised action localization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8679\u20138687","DOI":"10.1109\/ICCV.2019.00877"},{"issue":"1","key":"10650_CR115","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s10462-021-10033-z","volume":"55","author":"MV Narkhede","year":"2022","unstructured":"Narkhede MV, Bartakke PP, Sutaone MS (2022) A review on weight initialization strategies for neural networks. Artif intell Rev 55(1):291\u2013322","journal-title":"Artif intell Rev"},{"key":"10650_CR116","doi-asserted-by":"crossref","unstructured":"Nguyen P, Liu T, Prasad G, et\u00a0al (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":"10650_CR117","doi-asserted-by":"crossref","unstructured":"Niebles JC, Chen CW, Fei-Fei L (2010) Modeling temporal structure of decomposable motion segments for activity classification. In: European conference on computer vision, Springer, pp 392\u2013405","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"10650_CR118","doi-asserted-by":"crossref","unstructured":"Ning R, Zhang C, Zou Y (2021) Srf-net: Selective receptive field network for anchor-free temporal action detection. In: ICASSP 2021\u20132021 IEEE international conference on acoustics. Speech and Signal Processing (ICASSP), IEEE, pp 2460\u20132464","DOI":"10.1109\/ICASSP39728.2021.9414253"},{"key":"10650_CR119","doi-asserted-by":"crossref","unstructured":"Oneata D, Verbeek J, Schmid C (2014a) Efficient action localization with approximately normalized fisher vectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2545\u20132552","DOI":"10.1109\/CVPR.2014.326"},{"key":"10650_CR120","unstructured":"Oneata D, Verbeek J, Schmid C (2014b) The lear submission at thumos 2014. ECCV THUMOS Workshop (2014)"},{"key":"10650_CR121","unstructured":"Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"10650_CR122","doi-asserted-by":"crossref","unstructured":"Pan T, Song Y, Yang T, et\u00a0al (2021) Videomoco: Contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11,205\u201311,214","DOI":"10.1109\/CVPR46437.2021.01105"},{"issue":"3","key":"10650_CR123","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1007\/s10462-020-09904-8","volume":"54","author":"P Pareek","year":"2021","unstructured":"Pareek P, Thakkar A (2021) A survey on video-based human action recognition: recent updates, datasets, challenges, and applications. Artif Intell Rev 54(3):2259\u20132322","journal-title":"Artif Intell Rev"},{"key":"10650_CR124","first-page":"12,493","volume":"34","author":"M Patrick","year":"2021","unstructured":"Patrick M, Campbell D, Asano Y et al (2021) Keeping your eye on the ball: trajectory attention in video transformers. Adv Neural Inf Process Syst 34:12,493-12,506","journal-title":"Adv Neural Inf Process Syst"},{"key":"10650_CR125","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 (ECCV), pp 563\u2013579","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"10650_CR126","doi-asserted-by":"crossref","unstructured":"Qian R, Meng T, Gong B, et\u00a0al (2021) Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6964\u20136974","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"10650_CR127","doi-asserted-by":"crossref","unstructured":"Qing Z, Su H, Gan W, et\u00a0al (2021) Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 485\u2013494","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"10650_CR128","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3d residual networks. In: proceedings of the IEEE international conference on computer vision, pp 5533\u20135541","DOI":"10.1109\/ICCV.2017.590"},{"issue":"8","key":"10650_CR129","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"10650_CR130","unstructured":"Radford A, Narasimhan K, Salimans T, et al (2018) Improving language understanding by generative pre-training. OpenAI blog, 2018."},{"issue":"5","key":"10650_CR131","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy KK, Shah M (2013) Recognizing 50 human action categories of web videos. Mach Vis Appl 24(5):971\u2013981","journal-title":"Mach Vis Appl"},{"key":"10650_CR132","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et\u00a0al (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"10650_CR133","unstructured":"Ren S, He K, Girshick R, et al (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28:91\u201399, 2015."},{"key":"10650_CR134","doi-asserted-by":"crossref","unstructured":"Rodriguez MD, Ahmed J, Shah M (2008) Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: 2008 IEEE conference on computer vision and pattern recognition, IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"10650_CR135","doi-asserted-by":"crossref","unstructured":"Rother C, Minka T, Blake A, et\u00a0al (2006) Cosegmentation of image pairs by histogram matching-incorporating a global constraint into mrfs. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906), IEEE, pp 993\u20131000","DOI":"10.1109\/CVPR.2006.91"},{"key":"10650_CR136","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.aiopen.2022.01.001","volume":"3","author":"L Ruan","year":"2022","unstructured":"Ruan L, Jin Q (2022) Survey: transformer based video-language pre-training. AI Open 3:1\u201313","journal-title":"AI Open"},{"key":"10650_CR137","doi-asserted-by":"crossref","unstructured":"Sadanand S, Corso JJ (2012) Action bank: A high-level representation of activity in video. In: 2012 IEEE Conference on computer vision and pattern recognition, IEEE, pp 1234\u20131241","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"10650_CR138","unstructured":"Sanh V, Debut L, Chaumond J, et\u00a0al (2019) Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108"},{"key":"10650_CR139","doi-asserted-by":"crossref","unstructured":"Satkin S, Hebert M (2010) Modeling the temporal extent of actions. In: European conference on computer vision, Springer, pp 536\u2013548","DOI":"10.1007\/978-3-642-15549-9_39"},{"key":"10650_CR140","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local svm approach. In: Proceedings of the 17th international conference on pattern recognition, 2004. ICPR 2004., IEEE, pp 32\u201336","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"10650_CR141","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM international conference on Multimedia, pp 357\u2013360","DOI":"10.1145\/1291233.1291311"},{"key":"10650_CR142","doi-asserted-by":"publisher","first-page":"26146","DOI":"10.1109\/ACCESS.2019.2900753","volume":"7","author":"T Shao","year":"2019","unstructured":"Shao T, Guo Y, Chen H et al (2019) Transformer-based neural network for answer selection in question answering. IEEE Access 7:26146\u201326156","journal-title":"IEEE Access"},{"key":"10650_CR143","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. arXiv preprint arXiv:1511.04119"},{"key":"10650_CR144","doi-asserted-by":"crossref","unstructured":"Shi B, Dai Q, Mu Y, et\u00a0al (2020) Weakly-supervised action localization by generative attention modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1009\u20131019","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"10650_CR145","doi-asserted-by":"crossref","unstructured":"Shi D, Zhong Y, Cao Q, et\u00a0al (2022) React: Temporal action detection with relational queries. In: European conference on computer vision, Springer, pp 105\u2013121","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"10650_CR146","unstructured":"Shi X, Chen Z, Wang H, et al (2015) Convolutional lstm network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems, 802\u2013810."},{"key":"10650_CR147","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang SF (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":"10650_CR148","doi-asserted-by":"crossref","unstructured":"Shou Z, Gao H, Zhang L, et\u00a0al (2018) Autoloc: Weakly-supervised temporal action localization in untrimmed videos. In: Proceedings of the European conference on computer vision (ECCV), pp 154\u2013171","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"10650_CR149","doi-asserted-by":"crossref","unstructured":"Sigurdsson GA, Varol G, Wang X, et\u00a0al (2016) Hollywood in homes: Crowdsourcing data collection for activity understanding. In: European conference on computer vision, Springer, pp 510\u2013526","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"10650_CR150","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems, 27, 2014."},{"key":"10650_CR151","doi-asserted-by":"crossref","unstructured":"Singh KK, Xiao F, Lee YJ (2016) Track and transfer: Watching videos to simulate strong human supervision for weakly-supervised object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3548\u20133556","DOI":"10.1109\/CVPR.2016.386"},{"key":"10650_CR152","unstructured":"HO, Lee YJ, Jegelka S, et al (2014) Weakly-supervised discovery of visual pattern configurations. In Advances in Neural Information Processing Systems, pages 1637\u20131645, 2014."},{"key":"10650_CR153","unstructured":"Song Y, Vallmitjana J, Stent A, et\u00a0al (2015) Tvsum: Summarizing web videos using titles. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5179\u20135187"},{"key":"10650_CR154","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"key":"10650_CR155","unstructured":"Srivastava N, Mansimov E, Salakhudinov R (2015) Unsupervised learning of video representations using lstms. In: International conference on machine learning, PMLR, pp 843\u2013852"},{"key":"10650_CR156","doi-asserted-by":"crossref","unstructured":"Sudhakaran S, Escalera S, Lanz O (2019) Lsta: Long short-term attention for egocentric action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9954\u20139963","DOI":"10.1109\/CVPR.2019.01019"},{"key":"10650_CR157","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112","author":"Z Sun","year":"2022","unstructured":"Sun Z, Ke Q, Rahmani H et al (2022) Human action recognition from various data modalities: a review. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2022.3183112","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"10650_CR158","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1109\/TCSVT.2022.3201540","volume":"33","author":"W Sun","year":"2022","unstructured":"Sun W, Su R, Yu Q et al (2022) Slow motion matters: a slow motion enhanced network for weakly supervised temporal action localization. IEEE Trans Circ Syst Video Technol 33(1):354\u2013366","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"10650_CR159","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Xu Y, et\u00a0al (2019) How to fine-tune bert for text classification? In: China national conference on Chinese computational linguistics, Springer, pp 194\u2013206","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"10650_CR160","doi-asserted-by":"crossref","unstructured":"Tan J, Tang J, Wang L, et\u00a0al (2021) Relaxed transformer decoders for direct action proposal generation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13,526\u201313,535","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"10650_CR161","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, et\u00a0al (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10650_CR162","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, et\u00a0al (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"10650_CR163","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, et\u00a0al (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"10650_CR164","doi-asserted-by":"crossref","unstructured":"Truong TD, Bui QH, Duong CN, et\u00a0al (2022) Direcformer: A directed attention in transformer approach to robust action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 20,030\u201320,040","DOI":"10.1109\/CVPR52688.2022.01940"},{"key":"10650_CR165","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193611","author":"E Vahdani","year":"2022","unstructured":"Vahdani E, Tian Y (2022) Deep learning-based action detection in untrimmed videos: a survey. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2022.3193611","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR166","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke W, Vandenhende S, Georgoulis S, et\u00a0al (2021) Unsupervised semantic segmentation by contrasting object mask proposals. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10,052\u201310,062","DOI":"10.1109\/ICCV48922.2021.00990"},{"issue":"6","key":"10650_CR167","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2017","unstructured":"Varol G, Laptev I, Schmid C (2017) Long-term temporal convolutions for action recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1510\u20131517","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR168","unstructured":"Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In Advances in neural information processing systems, pp. 5998\u20136008, 2017."},{"issue":"1","key":"10650_CR169","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Kl\u00e4ser A, Schmid C et al (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103(1):60\u201379","journal-title":"Int J Comput Vis"},{"issue":"12","key":"10650_CR170","doi-asserted-by":"publisher","first-page":"5784","DOI":"10.3390\/app12125784","volume":"12","author":"Z Wang","year":"2022","unstructured":"Wang Z, Lu H, Jin J et al (2022) Human action recognition based on improved two-stream convolution network. Appl Sci 12(12):5784","journal-title":"Appl Sci"},{"key":"10650_CR171","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.eng.2021.03.023","volume":"18","author":"H Wang","year":"2021","unstructured":"Wang H, Wu H, He Z et al (2021) Progress in machine translation. Engineering 18:143\u2013153","journal-title":"Engineering"},{"key":"10650_CR172","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proceedings of the IEEE international conference on computer vision, pp 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"10650_CR173","doi-asserted-by":"crossref","unstructured":"Wang J, Jiao J, Liu YH (2020) Self-supervised video representation learning by pace prediction. In: European conference on computer vision, Springer, pp 504\u2013521","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"10650_CR174","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2014) Video action detection with relational dynamic-poselets. In: European conference on computer vision, Springer, pp 565\u2013580","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"10650_CR175","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X, et\u00a0al (2016a) Actionness estimation using hybrid fully convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2708\u20132717","DOI":"10.1109\/CVPR.2016.296"},{"key":"10650_CR176","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, et\u00a0al (2016b) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision, Springer, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"10650_CR177","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Lin D, et\u00a0al (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":"10650_CR178","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhang Y, Zheng Y, et\u00a0al (2022a) Rcl: recurrent continuous localization for temporal action detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13,566\u201313,575","DOI":"10.1109\/CVPR52688.2022.01320"},{"key":"10650_CR179","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, et\u00a0al (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10650_CR180","doi-asserted-by":"crossref","unstructured":"Wang X, Zhang R, Shen C, et\u00a0al (2021b) Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3024\u20133033","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"10650_CR181","doi-asserted-by":"crossref","unstructured":"Weinland D, Boyer E, Ronfard R (2007) Action recognition from arbitrary views using 3d exemplars. In: 2007 IEEE 11th international conference on computer vision, IEEE, pp 1\u20137","DOI":"10.1109\/ICCV.2007.4408849"},{"key":"10650_CR182","unstructured":"Wu J, Sun P, Chen S, et\u00a0al (2021) Towards high-quality temporal action detection with sparse proposals. arXiv preprint arXiv:2109.08847"},{"key":"10650_CR183","unstructured":"Wu Z, Xiong C, Jiang YG, et al (2019) Liteeval: a coarse-to-fine framework for resource efficient video recognition.  In Advances in Neural Information Processing Systems, 7778\u20137787."},{"key":"10650_CR184","doi-asserted-by":"publisher","first-page":"70477","DOI":"10.1109\/ACCESS.2020.2986861","volume":"8","author":"H Xia","year":"2020","unstructured":"Xia H, Zhan Y (2020) A survey on temporal action localization. IEEE Access 8:70477\u201370487","journal-title":"IEEE Access"},{"key":"10650_CR185","doi-asserted-by":"crossref","unstructured":"Xie E, Ding J, Wang W, et\u00a0al (2021) Detco: unsupervised contrastive learning for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8392\u20138401","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"10650_CR186","unstructured":"Xiong Y, Zhao Y, Wang L, et\u00a0al (2017) A pursuit of temporal accuracy in general activity detection. arXiv preprint arXiv:1703.02716"},{"key":"10650_CR187","first-page":"9923","volume":"34","author":"M Xu","year":"2021","unstructured":"Xu M, Perez Rua JM, Zhu X et al (2021) Low-fidelity video encoder optimization for temporal action localization. Adv Neural Inf Process Syst 34:9923\u20139935","journal-title":"Adv Neural Inf Process Syst"},{"key":"10650_CR188","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":"10650_CR189","doi-asserted-by":"crossref","unstructured":"Xu M, P\u00e9rez-R\u00faa JM, Escorcia V, et\u00a0al (2021a) Boundary-sensitive pre-training for temporal localization in videos. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7220\u20137230","DOI":"10.1109\/ICCV48922.2021.00713"},{"key":"10650_CR190","doi-asserted-by":"crossref","unstructured":"Xu Y, Zhang C, Cheng Z, et\u00a0al (2019) Segregated temporal assembly recurrent networks for weakly supervised multiple action detection. In: Proceedings of the AAAI conference on artificial intelligence, pp 9070\u20139078","DOI":"10.1609\/aaai.v33i01.33019070"},{"issue":"6","key":"10650_CR191","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1007\/s10462-019-09794-5","volume":"53","author":"A Yadav","year":"2020","unstructured":"Yadav A, Vishwakarma DK (2020) Sentiment analysis using deep learning architectures: a review. Artif Intell Rev 53(6):4335\u20134385","journal-title":"Artif Intell Rev"},{"key":"10650_CR192","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 et al (2020) Revisiting anchor mechanisms for temporal action localization. IEEE Trans Image Process 29:8535\u20138548","journal-title":"IEEE Trans Image Process"},{"key":"10650_CR193","doi-asserted-by":"crossref","unstructured":"Yang C, Wu Z, Zhou B, et\u00a0al (2021) Instance localization for self-supervised detection pretraining. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3987\u20133996","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"10650_CR194","doi-asserted-by":"crossref","unstructured":"Yeung S, Russakovsky O, Mori G, et\u00a0al (2016) End-to-end learning of action detection from frame glimpses in videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2678\u20132687","DOI":"10.1109\/CVPR.2016.293"},{"key":"10650_CR195","doi-asserted-by":"crossref","unstructured":"Yu G, Yuan J (2015) Fast action proposals for human action detection and search. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1302\u20131311","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"10650_CR196","doi-asserted-by":"crossref","unstructured":"Yu X, Hu W, Lu S, et\u00a0al (2019) Biobert based named entity recognition in electronic medical record. In: 2019 10th international conference on information technology in medicine and education (ITME), IEEE, pp 49\u201352","DOI":"10.1109\/ITME.2019.00022"},{"key":"10650_CR197","doi-asserted-by":"crossref","unstructured":"Yuan J, Ni B, Yang X, et\u00a0al (2016) Temporal action localization with pyramid of score distribution features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3093\u20133102","DOI":"10.1109\/CVPR.2016.337"},{"key":"10650_CR198","unstructured":"Yuan Y, Lyu Y, Shen X, et\u00a0al (2019) Marginalized average attentional network for weakly-supervised learning. arXiv preprint arXiv:1905.08586"},{"key":"10650_CR199","doi-asserted-by":"crossref","unstructured":"Yue-Hei\u00a0Ng J, Hausknecht M, Vijayanarasimhan S, et\u00a0al (2015) Beyond short snippets: Deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"10650_CR200","first-page":"11384","volume":"34","author":"X Zha","year":"2021","unstructured":"Zha X, Zhu W, Xun L et al (2021) Shifted chunk transformer for Spatio-temporal representational learning. Adv Neural Inf Process Syst 34:11384\u201311396","journal-title":"Adv Neural Inf Process Syst"},{"issue":"4","key":"10650_CR201","doi-asserted-by":"publisher","first-page":"4136","DOI":"10.1109\/TPAMI.2022.3189662","volume":"45","author":"Y Zhai","year":"2022","unstructured":"Zhai Y, Wang L, Tang W et al (2022) Adaptive two-stream consensus network for weakly-supervised temporal action localization. IEEE Trans Pattern Anal Mach Intell 45(4):4136\u20134151","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR202","doi-asserted-by":"crossref","unstructured":"Zhai Y, Wang L, Tang W, et\u00a0al (2020) Two-stream consensus network for weakly-supervised temporal action localization. In: European conference on computer vision, Springer, pp 37\u201354","DOI":"10.1007\/978-3-030-58539-6_3"},{"issue":"3","key":"10650_CR203","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1109\/TPAMI.2011.157","volume":"34","author":"Z Zhang","year":"2012","unstructured":"Zhang Z, Tao D (2012) Slow feature analysis for human action recognition. IEEE Trans Pattern Anal Mach Intell 34(3):436\u2013450","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10650_CR204","doi-asserted-by":"crossref","unstructured":"Zhang C, Yang T, Weng J, et\u00a0al (2022) Unsupervised pre-training for temporal action localization tasks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14,031\u201314,041","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"10650_CR205","doi-asserted-by":"crossref","unstructured":"Zhao Y, Xiong Y, Wang L, et\u00a0al (2017) Temporal action detection with structured segment networks. In: Proceedings of the IEEE international conference on computer vision, pp 2914\u20132923","DOI":"10.1109\/ICCV.2017.317"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-023-10650-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-023-10650-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-023-10650-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T12:11:46Z","timestamp":1708690306000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-023-10650-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":205,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["10650"],"URL":"https:\/\/doi.org\/10.1007\/s10462-023-10650-w","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,1]]},"assertion":[{"value":"19 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2024","order":2,"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":"Conflict of interest"}}],"article-number":"26"}}