{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:07:50Z","timestamp":1782317270459,"version":"3.54.5"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06518-x","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T23:51:37Z","timestamp":1744156297000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Optimal transport-based fusion of two-stream convolutional networks for action recognition"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6651-4360","authenticated-orcid":false,"given":"Sravani","family":"Yenduri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhavi","family":"Gudavalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gayathri","family":"C","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"6518_CR1","doi-asserted-by":"crossref","unstructured":"Islam Z, Rukonuzzaman M, Ahmed R, Kabir MH, Farazi M (2021) Efficient two-stream network for violence detection using separable convolutional lstm. In: 2021 International Joint Conference on Neural Networks, pp 1\u20138. IEEE","DOI":"10.1109\/IJCNN52387.2021.9534280"},{"key":"6518_CR2","doi-asserted-by":"crossref","unstructured":"Chang Y, Tu Z, Xie W, Luo B, Zhang S, Sui H, Yuan J (2022) Video anomaly detection with spatio-temporal dissociation. Pattern Recogn 122:108213","DOI":"10.1016\/j.patcog.2021.108213"},{"key":"6518_CR3","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":"6518_CR4","unstructured":"Andrej K, George T, Sanketh S, Thomas L, Rahul S, Li F-F (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1725\u20131732"},{"key":"6518_CR5","doi-asserted-by":"crossref","unstructured":"Girdhar R, Ramanan D, Gupta A, Sivic J, Russell B (2017) Actionvlad: Learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 971\u2013980","DOI":"10.1109\/CVPR.2017.337"},{"key":"6518_CR6","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.patrec.2014.07.011","volume":"49","author":"I Alexandros","year":"2014","unstructured":"Alexandros I, Anastastios T, Ioannis P (2014) Discriminant bag of words based representation for human action recognition. Pattern Recogn Lett 49:185\u2013192","journal-title":"Pattern Recogn Lett"},{"key":"6518_CR7","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. Adv Neural Inf Process Syst 27"},{"key":"6518_CR8","unstructured":"Lin J, Gan C, Han S (2018) Temporal shift module for efficient video understanding. CoRR arXiv:1811.08383 (1811)"},{"key":"6518_CR9","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2018) Temporal segment networks for action recognition in videos. IEEE Trans Pattern Anal Mach Intell 41(11):2740\u20132755","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"6518_CR10","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (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"},{"issue":"1\u20133","key":"6518_CR11","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) Determ Opt Flow Artif Intell 17(1\u20133):185\u2013203","journal-title":"Determ Opt Flow Artif Intell"},{"key":"6518_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"key":"6518_CR13","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"},{"issue":"2","key":"6518_CR14","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"},{"issue":"6","key":"6518_CR15","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":"6518_CR16","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.patcog.2018.08.007","volume":"86","author":"H Chen","year":"2019","unstructured":"Chen H, Li Y, Su D (2019) Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for rgb-d salient object detection. Pattern Recogn 86:376\u2013385","journal-title":"Pattern Recogn"},{"key":"6518_CR17","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1016\/j.neucom.2017.08.043","volume":"273","author":"N Zeng","year":"2018","unstructured":"Zeng N, Zhang H, Song B, Liu W, Li Y, Dobaie AM (2018) Facial expression recognition via learning deep sparse autoencoders. Neurocomput 273:643\u2013649","journal-title":"Neurocomput"},{"key":"6518_CR18","doi-asserted-by":"crossref","unstructured":"Lin J, Gan C, Han S (2019) 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":"6518_CR19","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (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":"6518_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2018.07.028","volume":"85","author":"H Yang","year":"2019","unstructured":"Yang H, Yuan C, Li B, Du Y, Xing J, Hu W, Maybank SJ (2019) Asymmetric 3d convolutional neural networks for action recognition. Pattern Recogn 85:1\u201312","journal-title":"Pattern Recogn"},{"key":"6518_CR21","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (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"},{"key":"6518_CR22","doi-asserted-by":"crossref","unstructured":"Li J, Liu X, Zhang M, Wang D (2020) Spatio-temporal deformable 3d convnets with attention for action recognition. Pattern Recogn 98:107037","DOI":"10.1016\/j.patcog.2019.107037"},{"key":"6518_CR23","doi-asserted-by":"crossref","unstructured":"Xiang W, Li C, Zhou Y, Wang B, Zhang L (2023) Generative action description prompts for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10276\u201310285","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"6518_CR24","doi-asserted-by":"crossref","unstructured":"Xu H, Gao Y, Hui Z, Li J, Gao X (2025) Language knowledge-assisted representation learning for skeleton-based action recognition. IEEE Trans Multimed","DOI":"10.1109\/TMM.2025.3543034"},{"key":"6518_CR25","doi-asserted-by":"crossref","unstructured":"Qu H, Cai Y, Liu J (2024) Llms are good action recognizers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18395\u201318406","DOI":"10.1109\/CVPR52733.2024.01741"},{"key":"6518_CR26","doi-asserted-by":"crossref","unstructured":"Gadzicki K, Khamsehashari R, Zetzsche C (2020) Early vs late fusion in multimodal convolutional neural networks. In: 2020 IEEE 23rd International Conference on Information Fusion (FUSION), pp 1\u20136","DOI":"10.23919\/FUSION45008.2020.9190246"},{"key":"6518_CR27","doi-asserted-by":"crossref","unstructured":"Lai Z, Zhang Y, Liang X (2024) A two-stream method for human action recognition using facial action cues. Sensors 24(21)","DOI":"10.3390\/s24216817"},{"key":"6518_CR28","doi-asserted-by":"crossref","unstructured":"Diba A, Sharma V, Van\u00a0Gool L (2017) Deep temporal linear encoding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2329\u20132338","DOI":"10.1109\/CVPR.2017.168"},{"key":"6518_CR29","unstructured":"Christoph R, Pinz FA (2016) Spatiotemporal residual networks for video action recognition. Adv Neural Inf Process Syst, 3468\u20133476"},{"key":"6518_CR30","doi-asserted-by":"publisher","first-page":"85284","DOI":"10.1109\/ACCESS.2020.2993227","volume":"8","author":"Y Wan","year":"2020","unstructured":"Wan Y, Yu Z, Wang Y, Li X (2020) Action recognition based on two-stream convolutional networks with long-short-term spatiotemporal features. IEEE Access 8:85284\u201385293","journal-title":"IEEE Access"},{"key":"6518_CR31","doi-asserted-by":"crossref","unstructured":"Dai C, Liu X, Lai J (2020) Human action recognition using two-stream attention based lstm networks. Appl Soft Comput 86:105820","DOI":"10.1016\/j.asoc.2019.105820"},{"key":"6518_CR32","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":"6518_CR33","unstructured":"Cuturi M (2013) Sinkhorn distances: Lightspeed computation of optimal transport. Adv Neural Inf Process Syst 26"},{"issue":"2","key":"6518_CR34","doi-asserted-by":"publisher","first-page":"343","DOI":"10.2140\/pjm.1967.21.343","volume":"21","author":"R Sinkhorn","year":"1967","unstructured":"Sinkhorn R, Knopp P (1967) Concerning nonnegative matrices and doubly stochastic matrices. Pacific J Math 21(2):343\u2013348","journal-title":"Pacific J Math"},{"key":"6518_CR35","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"6518_CR36","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: 2011 International Conference on Computer Vision, pp 2556\u20132563. IEEE","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"6518_CR37","doi-asserted-by":"crossref","unstructured":"Goyal R, Ebrahimi\u00a0Kahou S, Michalski V, Materzynska J, Westphal S, Kim H, Haenel V, Fruend I, Yianilos P, Mueller-Freitag M, et al. (2017) The\" something something\" video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp 5842\u20135850","DOI":"10.1109\/ICCV.2017.622"},{"key":"6518_CR38","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev P, et al. (2017) The kinetics human action video dataset. arXiv:1705.06950"},{"key":"6518_CR39","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patrec.2018.07.011","volume":"112","author":"H Kwon","year":"2018","unstructured":"Kwon H, Kim Y, Lee JS, Cho M (2018) First person action recognition via two-stream convnet with long-term fusion pooling. Pattern Recogn Lett 112:161\u2013167","journal-title":"Pattern Recogn Lett"},{"key":"6518_CR40","doi-asserted-by":"crossref","unstructured":"Tran A, Cheong L-F (2017) Two-stream flow-guided convolutional attention networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp 3110\u20133119","DOI":"10.1109\/ICCVW.2017.368"},{"key":"6518_CR41","doi-asserted-by":"crossref","unstructured":"Zhu J, Zou W, Zhu Z (2018) Two-stream gated fusion convnets for action recognition. In: 2018 24th International Conference on Pattern Recognition, pp 597\u2013602. IEEE","DOI":"10.1109\/ICPR.2018.8545639"},{"key":"6518_CR42","doi-asserted-by":"crossref","unstructured":"Jiang B, Wang M, Gan W, Wu W, Yan J (2019) Stm: Spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2000\u20132009","DOI":"10.1109\/ICCV.2019.00209"},{"key":"6518_CR43","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (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":"6518_CR44","doi-asserted-by":"crossref","unstructured":"Fan H, Xiong B, Mangalam K, Li Y, Yan Z, Malik J, Feichtenhofer C (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":"6518_CR45","doi-asserted-by":"crossref","unstructured":"Wang L, Huang B, Zhao Z, Tong Z, He Y, Wang Y, Wang Y, Qiao Y (2023) Videomae v2: Scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14549\u201314560","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"6518_CR46","doi-asserted-by":"crossref","unstructured":"Wang R, Chen D, Wu Z, Chen Y, Dai X, Liu M, Yuan L, Jiang Y-G (2023) Masked video distillation: Rethinking masked feature modeling for self-supervised video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6312\u20136322","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"6518_CR47","unstructured":"Lu H, Jian H, Poppe R, Salah AA (2024) Enhancing video transformers for action understanding with vlm-aided training. arXiv:2403.16128"},{"key":"6518_CR48","doi-asserted-by":"crossref","unstructured":"Srivastava S, Sharma G (2024) Omnivec2-a novel transformer based network for large scale multimodal and multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 27412\u201327424","DOI":"10.1109\/CVPR52733.2024.02588"},{"key":"6518_CR49","doi-asserted-by":"crossref","unstructured":"Wang Y, Li K, Li X, Yu J, He Y, Chen G, Pei B, Zheng R, Wang Z, Shi Y, et al. (2024) Internvideo2: Scaling foundation models for multimodal video understanding. In: European Conference on Computer Vision, pp 396\u2013416. Springer","DOI":"10.1007\/978-3-031-73013-9_23"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06518-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06518-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06518-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:35:44Z","timestamp":1758310544000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06518-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":49,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6518"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06518-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]},"assertion":[{"value":"26 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2025","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 that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper. This work was done as part of the corresponding author\u2019s research during her PhD course at IITH.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interests"}}],"article-number":"641"}}