{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:33:03Z","timestamp":1768073583560,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2021YFE0205400"],"award-info":[{"award-number":["2021YFE0205400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871434"],"award-info":[{"award-number":["61871434"]}],"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":["61976098"],"award-info":[{"award-number":["61976098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation for Outstanding Young Scholars of Fujian Province","award":["2022J06023"],"award-info":[{"award-number":["2022J06023"]}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2022J01294"],"award-info":[{"award-number":["2022J01294"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Platform Project of Fuzhou-Xiamen- Quanzhou National Independent Innovation Demonstration Zone","award":["2021FX03"],"award-info":[{"award-number":["2021FX03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00521-023-09333-y","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T11:02:34Z","timestamp":1703588554000},"page":"5077-5091","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised video-based action recognition using two-stream generative adversarial network"],"prefix":"10.1007","volume":"36","author":[{"given":"Wei","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2802-7745","authenticated-orcid":false,"given":"Huanqiang","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Jianqing","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Chih-Hsien","family":"Hsia","sequence":"additional","affiliation":[]},{"given":"Junhui","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Kai-Kuang","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"issue":"10","key":"9333_CR1","doi-asserted-by":"publisher","first-page":"7489","DOI":"10.1007\/s00521-021-06875-x","volume":"34","author":"G Ciaparrone","year":"2022","unstructured":"Ciaparrone G, Chiariglione L, Tagliaferri R (2022) A comparison of deep learning models for end-to-end face-based video retrieval in unconstrained videos. Neural Comput Appl 34(10):7489\u20137506","journal-title":"Neural Comput Appl"},{"issue":"6","key":"9333_CR2","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1007\/s00521-020-05081-5","volume":"33","author":"A Kompella","year":"2021","unstructured":"Kompella A, Kulkarni R (2021) A semi-supervised recurrent neural network for video salient object detection. Neural Comput Appl 33(6):2065\u20132083","journal-title":"Neural Comput Appl"},{"issue":"23","key":"9333_CR3","doi-asserted-by":"publisher","first-page":"16439","DOI":"10.1007\/s00521-021-06239-5","volume":"33","author":"Y Hou","year":"2021","unstructured":"Hou Y, Yu H, Zhou D, Wang P, Ge H, Zhang J, Zhang Q (2021) Local-aware spatio-temporal attention network with multi-stage feature fusion for human action recognition. Neural Comput Appl 33(23):16439\u201316450","journal-title":"Neural Comput Appl"},{"issue":"15","key":"9333_CR4","doi-asserted-by":"publisher","first-page":"9375","DOI":"10.1007\/s00521-021-05698-0","volume":"33","author":"M Tong","year":"2021","unstructured":"Tong M, Yan K, Jin L, Yue X, Li M (2021) Dm-ctsa: a discriminative multi-focused and complementary temporal\/spatial attention framework for action recognition. Neural Comput Appl 33(15):9375\u20139389","journal-title":"Neural Comput Appl"},{"issue":"5","key":"9333_CR5","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.1109\/TCSVT.2022.3221280","volume":"33","author":"W Lin","year":"2023","unstructured":"Lin W, Liu X, Zhuang Y, Ding X, Tu X, Huang Y, Zeng H (2023) Unsupervised video-based action recognition with imagining motion and perceiving appearance. IEEE Trans Circuits Syst Video Technol 33(5):2245\u20132258","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9333_CR6","doi-asserted-by":"crossref","unstructured":"Sun C, Nagrani A, Tian Y, Schmid C (2021) Composable augmentation encoding for video representation learning. arXiv preprint arXiv:2104.00616","DOI":"10.1109\/ICCV48922.2021.00871"},{"key":"9333_CR7","doi-asserted-by":"crossref","unstructured":"Qian R, Meng T, Gong B, Yang MH, Wang H, Belongie S, Cui Y (2021) Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6964\u20136974","DOI":"10.1109\/CVPR46437.2021.00689"},{"issue":"8","key":"9333_CR8","doi-asserted-by":"publisher","first-page":"5266","DOI":"10.1109\/TCSVT.2022.3141051","volume":"32","author":"L Tao","year":"2022","unstructured":"Tao L, Wang X, Yamasaki T (2022) An improved inter-intra contrastive learning framework on self-supervised video representation. IEEE Trans Circuits Syst Video Technol 32(8):5266\u20135280","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9333_CR9","doi-asserted-by":"crossref","unstructured":"Dorkenwald M, Xiao F, Brattoli B, Tighe J, Modolo D (2022) Scvrl: shuffled contrastive video representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4132\u20134141","DOI":"10.1109\/CVPRW56347.2022.00458"},{"key":"9333_CR10","doi-asserted-by":"crossref","unstructured":"Ding S, Li M, Yang T, Qian R, Xu H, Chen Q, Wang J, Xiong H (2022) Motion-aware contrastive video representation learning via foreground-background merging. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9716\u20139726","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"9333_CR11","doi-asserted-by":"crossref","unstructured":"Park J, Lee J, Kim I, Sohn K (2022) Probabilistic representations for video contrastive learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14711\u201314721","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"9333_CR12","doi-asserted-by":"crossref","unstructured":"Ni J, Zhou N, Qin J, Wu Q, Liu J, Li B, Huang D (2022) Motion sensitive contrastive learning for self-supervised video representation. In: European conference on computer vision. Springer, pp 457\u2013474","DOI":"10.1007\/978-3-031-19833-5_27"},{"key":"9333_CR13","doi-asserted-by":"crossref","unstructured":"Ahsan U, Madhok R, Essa I (2019) Video jigsaw: Unsupervised learning of spatiotemporal context for video action recognition. In: IEEE winter conference on applications of computer vision. IEEE, pp 179\u2013189","DOI":"10.1109\/WACV.2019.00025"},{"key":"9333_CR14","doi-asserted-by":"crossref","unstructured":"Knights J, Harwood B, Ward D, Vanderkop A, Mackenzie-Ross O, Moghadam P (2021) Temporally coherent embeddings for self-supervised video representation learning. In: International conference on pattern recognition. IEEE, pp 8914\u20138921","DOI":"10.1109\/ICPR48806.2021.9412071"},{"key":"9333_CR15","doi-asserted-by":"crossref","unstructured":"Huo Y, Ding M, Lu H, Huang Z, Tang M, Lu Z, Xiang T (2021) Self-supervised video representation learning with constrained spatiotemporal jigsaw. In: International joint conference on artificial intelligence. IEEE","DOI":"10.24963\/ijcai.2021\/104"},{"key":"9333_CR16","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhang H, Wu G, Li J (2022) Spatio-temporal self-supervision enhanced transformer networks for action recognition. In: IEEE international conference on multimedia and Expo. IEEE, pp 1\u20136","DOI":"10.1109\/ICME52920.2022.9859741"},{"key":"9333_CR17","doi-asserted-by":"crossref","unstructured":"Duan H, Zhao N, Chen K, Lin D (2022) Transrank: Self-supervised video representation learning via ranking-based transformation recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3000\u20133010","DOI":"10.1109\/CVPR52688.2022.00301"},{"key":"9333_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3293727","author":"Z Chen","year":"2023","unstructured":"Chen Z, Wang H, Chen C (2023) Self-supervised video representation learning by serial restoration with elastic complexity. IEEE Trans Multimed. https:\/\/doi.org\/10.1109\/TMM.2023.3293727","journal-title":"IEEE Trans Multimed"},{"key":"9333_CR19","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"key":"9333_CR20","unstructured":"Ahsan U, Sun C, Essa I (2018) Discrimnet: Semi-supervised action recognition from videos using generative adversarial networks. In: IEEE conference on computer vision and pattern recognition"},{"issue":"6","key":"9333_CR21","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":"9333_CR22","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. In: IEEE conference on computer vision and pattern recognition, pp 4768\u20134777","DOI":"10.1109\/CVPR.2017.787"},{"key":"9333_CR23","doi-asserted-by":"crossref","unstructured":"Hara K, Kataoka H, Satoh Y (2018) Can spatiotemporal 3d CNNs retrace the history of 2d CNNs and imagenet? In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6546\u20136555","DOI":"10.1109\/CVPR.2018.00685"},{"issue":"5","key":"9333_CR24","first-page":"2760","volume":"44","author":"J Lin","year":"2020","unstructured":"Lin J, Gan C, Wang K, Han S (2020) TSM: temporal shift module for efficient and scalable video understanding on edge devices. IEEE Trans Pattern Anal Mach Intell 44(5):2760\u20132774","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9333_CR25","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/TMM.2021.3057503","volume":"24","author":"L Zhu","year":"2022","unstructured":"Zhu L, Fan H, Luo Y, Xu M, Yang Y (2022) Temporal cross-layer correlation mining for action recognition. IEEE Trans Multimedia 24:668\u2013676","journal-title":"IEEE Trans Multimedia"},{"key":"9333_CR26","unstructured":"Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. Proc Int Confer Learn Represent, pp 1-16"},{"key":"9333_CR27","volume-title":"The perception of the visual world","author":"JJ Gibson","year":"1950","unstructured":"Gibson JJ (1950) The perception of the visual world. Houghton Mifflin"},{"key":"9333_CR28","unstructured":"Gibson JJ, Carmichael L (1966) The senses considered as perceptual systems 2(1). Houghton Mifflin"},{"issue":"1\u20133","key":"9333_CR29","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BK Horn","year":"1981","unstructured":"Horn BK, Schunck BG (1981) Determining optical flow. Artif Intell 17(1\u20133):185\u2013203","journal-title":"Artif Intell"},{"key":"9333_CR30","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":"9333_CR31","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) Hmdb: a large video database for human motion recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"9333_CR32","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467"},{"key":"9333_CR33","doi-asserted-by":"crossref","unstructured":"Kim D, Cho D, Kweon IS (2019) Self-supervised video representation learning with space-time cubic puzzles. In: Proceedings of the aaai conference on artificial intelligence, vol 33, pp 8545\u20138552","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"9333_CR34","unstructured":"Vondrick C, Pirsiavash H, Torralba A (2016) Generating videos with scene dynamics. In: Advances in neural information processing systems, pp 613\u2013621"},{"key":"9333_CR35","doi-asserted-by":"crossref","unstructured":"Behrmann N, Gall J, Noroozi M (2021) Unsupervised video representation learning by bidirectional feature prediction. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1670\u20131679","DOI":"10.1109\/WACV48630.2021.00171"},{"key":"9333_CR36","doi-asserted-by":"crossref","unstructured":"Misra I, Zitnick CL, Hebert M (2016) Shuffle and learn: unsupervised learning using temporal order verification. In: Proceedings of European conference on computer vision, pp 527\u2013544","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"9333_CR37","doi-asserted-by":"crossref","unstructured":"Wang X, Gupta A (2015) Unsupervised learning of visual representations using videos. In: Proceedings of the IEEE international conference on computer vision, pp 2794\u20132802","DOI":"10.1109\/ICCV.2015.320"},{"key":"9333_CR38","doi-asserted-by":"crossref","unstructured":"He KM, Fan HQ, Wu YX, Xie SN, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"9333_CR39","doi-asserted-by":"crossref","unstructured":"Gan C, Gong B, Liu K, Su H, Guibas LJ (2018) Geometry guided convolutional neural networks for self-supervised video representation learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5589\u20135597","DOI":"10.1109\/CVPR.2018.00586"},{"key":"9333_CR40","doi-asserted-by":"crossref","unstructured":"Wei D, Lim J, Zisserman A, Freeman W (2018) Learning and using the arrow of time. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8052\u20138060","DOI":"10.1109\/CVPR.2018.00840"},{"key":"9333_CR41","doi-asserted-by":"crossref","unstructured":"Buchler U, Brattoli B, Ommer B (2018) Improving spatiotemporal self-supervision by deep reinforcement learning. In: Proceedings of the European conference on computer vision, pp 770\u2013786","DOI":"10.1007\/978-3-030-01267-0_47"},{"key":"9333_CR42","doi-asserted-by":"crossref","unstructured":"Wang J, Jiao J, Bao L, He S, Liu Y, Liu W (2019) Self-supervised spatio-temporal representation learning for videos by predicting motion and appearance statistics. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4006\u20134015","DOI":"10.1109\/CVPR.2019.00413"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09333-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09333-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09333-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T10:15:03Z","timestamp":1708164903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09333-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"references-count":42,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["9333"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09333-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"31 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, and there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled \u2018Unsupervised Video-Based Action Recognition Using Two-Stream Generative Adversarial Network.\u2019","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}