{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:19:45Z","timestamp":1776885585507,"version":"3.51.2"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:00:00Z","timestamp":1768608000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:00:00Z","timestamp":1768608000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11263-025-02605-1","type":"journal-article","created":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T05:03:22Z","timestamp":1768626202000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Selective Volume Mixup for Video Action Recognition"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8670-1312","authenticated-orcid":false,"given":"Yi","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofan","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"key":"2605_CR1","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. Iccv (pp. 6836\u20136846).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"2605_CR2","unstructured":"Bertasius, G., Wang, H., & Torresani, L. (2021). Is space-time attention all you need for video understanding? Icml (Vol.\u00a02, p.4)."},{"key":"2605_CR3","unstructured":"Carratino, L., Ciss\u00e9, M., Jenatton, R., & Vert, J.-P. (2022). On mixup regularization. Journal of machine learning research,23(325), 1\u201331."},{"key":"2605_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. Cvpr (pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"2605_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Panda, R., Ramakrishnan, K., Feris, R., Cohn, J., Oliva, A., & Fan, Q. (2021). Deep analysis of cnn-based spatio-temporal representations for action recognition. Cvpr (pp. 6165\u20136175).","DOI":"10.1109\/CVPR46437.2021.00610"},{"key":"2605_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J.-N., Sun, S., He, J., Torr, P.H., Yuille, A., & Bai, S. (2022). Transmix: Attend to mix for vision transformers. Cvpr (pp. 12135\u201312144).","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"2605_CR7","unstructured":"Contributors, M. (2020). Openmmlab\u2019s next generation video understanding toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmaction2."},{"key":"2605_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q.V. (2018). Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501","DOI":"10.1109\/CVPR.2019.00020"},{"key":"2605_CR9","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., & Le, Q.V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. Cvpr workshops (pp. 702\u2013703).","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2605_CR10","unstructured":"DeVries, T., & Taylor, G.W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552."},{"key":"2605_CR11","unstructured":"Diba, A., Fayyaz, M., Sharma, V., Hossein\u00a0Karami, A., Mahdi\u00a0Arzani, M., Yousefzadeh, R., & Van\u00a0Gool, L. (2018). Temporal 3d convnets using temporal transition layer. Cvpr workshops (pp. 1117\u20131121)."},{"key":"2605_CR12","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., & Van\u00a0Gool, L. (2017). Deep temporal linear encoding networks. Cvpr (pp. 2329\u20132338).","DOI":"10.1109\/CVPR.2017.168"},{"key":"2605_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. Iclr."},{"key":"2605_CR14","unstructured":"Fan, H., Li, Y., Xiong, B., Lo, W-Y., Feichtenhofer, C. (2020). Pyslowfast. https:\/\/github.com\/facebookresearch\/slowfast."},{"key":"2605_CR15","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021). Multiscale vision transformers. Iccv (pp. 6824\u20136835).","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"2605_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020). X3d: Expanding architectures for efficient video recognition. Cvpr (pp. 203\u2013213).","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2605_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019). Slowfast networks for video recognition. Iccv (pp. 6202\u20136211).","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2605_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2016). Convolutional two-stream network fusion for video action recognition. Cvpr (p.1933-1941).","DOI":"10.1109\/CVPR.2016.213"},{"key":"2605_CR19","unstructured":"Gontijo-Lopes, R., Smullin, S., Cubuk, E.D., & Dyer, E. (2021). Tradeoffs in data augmentation: An empirical study. Iclr."},{"key":"2605_CR20","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Keller, F., & Sevilla-Lara, L. (2022). Learn2augment: learning to composite videos for data augmentation in action recognition. Eccv (pp. 242\u2013259).","DOI":"10.1007\/978-3-031-19821-2_14"},{"key":"2605_CR21","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. (2017). The\" something something\" video database for learning and evaluating visual common sense. Iccv (pp. 5842\u20135850).","DOI":"10.1109\/ICCV.2017.622"},{"key":"2605_CR22","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z.,& Gheshlaghi Azar, M. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Neurips (Vol.\u00a033, pp. 21271\u201321284)."},{"key":"2605_CR23","doi-asserted-by":"crossref","unstructured":"Hao, X., Zhu, Y., Appalaraju, S., Zhang, A., Zhang, W., Li, B., & Li, M. (2023). Mixgen: A new multi-modal data augmentation. Wacv (pp. 379\u2013389).","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"2605_CR24","doi-asserted-by":"publisher","first-page":"7279","DOI":"10.1109\/TIP.2022.3221292","volume":"31","author":"Y Hao","year":"2022","unstructured":"Hao, Y., Wang, S., Tan, Y., He, X., Liu, Z., & Wang, M. (2022). Spatio-temporal collaborative module for efficient action recognition. IEEE Trans. Image Process.,31, 7279\u20137291.","journal-title":"IEEE Trans. Image Process."},{"issue":"5820","key":"2605_CR25","first-page":"5840","volume":"132","author":"Y Hao","year":"2024","unstructured":"Hao, Y., Zhou, D., Wang, Z., Ngo, C.-W., & Wang, M. (2024). Posmlp-video: Spatial and temporal relative position encoding for efficient video recognition. International Journal of Computer Vision,132(5820), 5840.","journal-title":"International Journal of Computer Vision"},{"key":"2605_CR26","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., & Lakshminarayanan, B. (2020). Augmix: A simple data processing method to improve robustness and uncertainty. Iclr."},{"key":"2605_CR27","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K.Q. (2016). Deep networks with stochastic depth. Eccv (pp. 646\u2013661).","DOI":"10.1007\/978-3-319-46493-0_39"},{"issue":"4","key":"2605_CR28","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1109\/TIP.2018.2877936","volume":"28","author":"W Huang","year":"2018","unstructured":"Huang, W., Fan, L., Harandi, M., Ma, L., Liu, H., Liu, W., & Gan, C. (2018). Toward efficient action recognition: Principal backpropagation for training two-stream networks. IEEE Trans. Image Process.,28(4), 1773\u20131782.","journal-title":"IEEE Trans. Image Process."},{"key":"2605_CR29","doi-asserted-by":"crossref","unstructured":"Hussein, N., Gavves, E., & Smeulders, A.W. (2019). Timeception for complex action recognition. Cvpr (pp. 254\u2013263).","DOI":"10.1109\/CVPR.2019.00034"},{"issue":"1","key":"2605_CR30","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., & Yu, K. (2012). 3d convolutional neural networks for human action recognition. IEEE trans. on PAMI,35(1), 221\u2013231.","journal-title":"IEEE trans. on PAMI"},{"key":"2605_CR31","unstructured":"Kim, T., Kim, J., Shim, M., Yun, S., Kang, M., Wee, D., & Lee, S. (2023). Exploring temporally dynamic data augmentation for video recognition. Iclr."},{"key":"2605_CR32","doi-asserted-by":"crossref","unstructured":"Kim, T., Lee, H., Cho, M., Lee, H.S., Cho, D.H., & Lee, S. (2020). Learning temporally invariant and localizable features via data augmentation for video recognition. Eccv workshops (pp. 386\u2013403).","DOI":"10.1007\/978-3-030-66096-3_27"},{"key":"2605_CR33","unstructured":"Li, K., Wang, Y., Peng, G., Song, G., Liu, Y., Li, H., & Qiao, Y. (2022). Uniformer: Unified transformer for efficient spatial-temporal representation learning. Iclr."},{"key":"2605_CR34","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., & Hwang, J.-N. (2022). Grounded language-image pre-training. Cvpr (pp. 10965\u201310975).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"2605_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., & Vasconcelos, N. (2018a). Resound: Towards action recognition without representation bias. Eccv (pp. 513\u2013528).","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"2605_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., & Rehg, J.M. (2018b). In the eye of beholder: Joint learning of gaze and actions in first person video. Eccv (pp. 619\u2013635).","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"2605_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., & Feichtenhofer, C. (2022). Mvitv2: Improved multiscale vision transformers for classification and detection. Cvpr (pp. 4804\u20134814).","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"2605_CR38","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., & Han, S. (2019). Tsm: Temporal shift module for efficient video understanding. Iccv (pp. 7083\u20137093).","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2605_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, S., Wu, D., Liu, Z., Chen, Z., Wu, L., & Li, S.Z. (2022). Automix: Unveiling the power of mixup for stronger classifiers. Eccv (pp. 441\u2013458).","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"2605_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. Iccv (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2605_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A convnet for the 2020s. Cvpr (pp. 11976\u201311986).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2605_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. Cvpr (pp. 3202\u20133211).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2605_CR43","doi-asserted-by":"crossref","unstructured":"Long, F., Qiu, Z., Pan, Y., Yao, T., Luo, J., & Mei, T. (2022a). Stand-alone inter-frame attention in video models. Cvpr (pp. 3192\u20133201).","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"2605_CR44","doi-asserted-by":"crossref","unstructured":"Long, F., Qiu, Z., Pan, Y., Yao, T., Ngo, C-W., & Mei, T. (2022b). Dynamic temporal filtering in video models. Eccv (pp. 475\u2013492).","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"2605_CR45","unstructured":"Loshchilov, I., & Hutter, F. (2017a). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 ,"},{"key":"2605_CR46","unstructured":"Loshchilov, I., & Hutter, F. (2017b). Fixing weight decay regularization in adam. arXiv preprintarXiv:1711.05101 ,"},{"issue":"8","key":"2605_CR47","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1109\/TIP.2019.2901707","volume":"28","author":"M Lu","year":"2019","unstructured":"Lu, M., Li, Z.-N., Wang, Y., & Pan, G. (2019). Deep attention network for egocentric action recognition. IEEE Trans. Image Process.,28(8), 3703\u20133713.","journal-title":"IEEE Trans. Image Process."},{"key":"2605_CR48","unstructured":"Ma, C., & Ying, L. (2021). On linear stability of sgd and input-smoothness of neural networks. Neurips (Vol.\u00a034, pp. 16805\u201316817)."},{"key":"2605_CR49","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S-M., Fawzi, A., Uesato, J., & Frossard, P. (2019). Robustness via curvature regularization, and vice versa. Cvpr (pp. 9078\u20139086).","DOI":"10.1109\/CVPR.2019.00929"},{"key":"2605_CR50","unstructured":"Mustafa, W., Vandermeulen, R.A., Kloft, M. (2020). Input hessian regularization of neural networks. arXiv preprint arXiv:2009.06571 ,"},{"key":"2605_CR51","doi-asserted-by":"crossref","unstructured":"Naveed, H., Anwar, S., Hayat, M., Javed, K., & Mian, A. (2024). Survey: Image mixing and deleting for data augmentation. Engineering Applications of Artificial Intelligence,131, Article 107791.","DOI":"10.1016\/j.engappai.2023.107791"},{"key":"2605_CR52","unstructured":"Park, C., Yun, S., & Chun, S. (2022). A unified analysis of mixed sample data augmentation: a loss function perspective. Neurips (Vol.\u00a035, pp. 35504\u201335518)."},{"key":"2605_CR53","doi-asserted-by":"crossref","unstructured":"Park, J., Yang, J.Y., Shin, J., Hwang, S.J., & Yang, E. (2022). Saliency grafting: Innocuous attribution-guided mixup with calibrated label mixing. Aaai (Vol.\u00a036, pp. 7957\u20137965).","DOI":"10.1609\/aaai.v36i7.20766"},{"key":"2605_CR54","unstructured":"Patrick, M., Campbell, D., Asano, Y., Misra, I., Metze, F., Feichtenhofer, C., & Henriques, J.F. (2021). Keeping your eye on the ball: Trajectory attention in video transformers. Neurips (Vol.\u00a034, pp. 12493\u201312506)."},{"key":"2605_CR55","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., & Mei, T. (2017a). Deep quantization: Encoding convolutional activations with deep generative model. Cvpr (pp. 6759\u20136768).","DOI":"10.1109\/CVPR.2017.435"},{"key":"2605_CR56","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., & Mei, T. (2017b). Learning spatio-temporal representation with pseudo-3d residual networks. Iccv (pp. 5533\u20135541).","DOI":"10.1109\/ICCV.2017.590"},{"key":"2605_CR57","unstructured":"Qiu, Z., Yao, T., Ngo, C-W., & Mei, T. (2021). Optimization planning for 3d convnets. Icml (pp. 8726\u20138736)."},{"key":"2605_CR58","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Ngo, C-W., & Mei, T. (2022). Mlp-3d: A mlp-like 3d architecture with grouped time mixing. Cvpr (pp. 3062\u20133072).","DOI":"10.1109\/CVPR52688.2022.00307"},{"key":"2605_CR59","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Ngo, C-W., Tian, X., & Mei, T. (2019). Learning spatio-temporal representation with local and global diffusion. Cvpr (pp. 12056\u201312065).","DOI":"10.1109\/CVPR.2019.01233"},{"key":"2605_CR60","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., & Clark, J. (2021). Learning transferable visual models from natural language supervision. Icml (pp. 8748\u20138763)."},{"key":"2605_CR61","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. Nips (pp. 1933\u20131941)."},{"key":"2605_CR62","unstructured":"Soomro, K., Zamir, A.R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 ,"},{"issue":"1","key":"2605_CR63","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. JMLR,15(1), 1929\u20131958.","journal-title":"JMLR"},{"key":"2605_CR64","doi-asserted-by":"crossref","unstructured":"Tan, Y., Hao, Y., He, X., Wei, Y., & Yang, X. (2021). Selective dependency aggregation for action classification. Acm mm (pp. 592\u2013601).","DOI":"10.1145\/3474085.3475218"},{"key":"2605_CR65","doi-asserted-by":"crossref","unstructured":"Tan, Y., Hao, Y., Zhang, H., Wang, S., & He, X. (2022). Hierarchical hourglass convolutional network for efficient video classification. Acm mm (pp. 5880\u20135891).","DOI":"10.1145\/3503161.3547841"},{"issue":"10","key":"2605_CR66","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1007\/s11263-022-01661-1","volume":"130","author":"Y Tian","year":"2022","unstructured":"Tian, Y., Yan, Y., Zhai, G., Guo, G., & Gao, Z. (2022). Ean: event adaptive network for enhanced action recognition. International Journal of Computer Vision,130(10), 2453\u20132471.","journal-title":"International Journal of Computer Vision"},{"key":"2605_CR67","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. Iccv (pp. 4489\u20134497).","DOI":"10.1109\/ICCV.2015.510"},{"key":"2605_CR68","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., & Feiszli, M. (2019). Video classification with channel-separated convolutional networks. Iccv (pp. 5552\u20135561).","DOI":"10.1109\/ICCV.2019.00565"},{"key":"2605_CR69","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. Cvpr (pp. 6450\u20136459).","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"6","key":"2605_CR70","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., & Schmid, C. (2018). Long-term temporal convolutions for action recognition. IEEE Trans. on PAMI,40(6), 1510\u20131517.","journal-title":"IEEE Trans. on PAMI"},{"key":"2605_CR71","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van\u00a0Gool, L. (2016). Temporal segment networks: Towards good practices for deep action recognition. Eccv (pp. 20\u201336).","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"2605_CR72","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., & Feiszli, M. (2020). What makes training multi-modal classification networks hard? Cvpr (pp. 12695\u201312705).","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"2605_CR73","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. Cvpr (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2605_CR74","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018). Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. Eccv (pp. 305\u2013321).","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"2605_CR75","doi-asserted-by":"crossref","unstructured":"Xing, Z., Dai, Q., Hu, H., Chen, J., Wu, Z., & Jiang, Y-G. (2023). Svformer: Semi-supervised video transformer for action recognition. Cvpr (pp. 18816\u201318826).","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"2605_CR76","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., & Schmid, C. (2022). Multiview transformers for video recognition. Cvpr (pp. 3333\u20133343).","DOI":"10.1109\/CVPR52688.2022.00333"},{"issue":"10","key":"2605_CR77","doi-asserted-by":"publisher","first-page":"2984","DOI":"10.1109\/TIP.2015.2438540","volume":"24","author":"Y Yan","year":"2015","unstructured":"Yan, Y., Ricci, E., Liu, G., & Sebe, N. (2015). Egocentric daily activity recognition via multitask clustering. IEEE Trans. Image Process.,24(10), 2984\u20132995.","journal-title":"IEEE Trans. Image Process."},{"key":"2605_CR78","doi-asserted-by":"publisher","first-page":"5783","DOI":"10.1109\/TIP.2020.2984904","volume":"29","author":"H Yang","year":"2020","unstructured":"Yang, H., Yuan, C., Zhang, L., Sun, Y., Hu, W., & Maybank, S. J. (2020). Sta-cnn: Convolutional spatial-temporal attention learning for action recognition. IEEE Trans. Image Process.,29, 5783\u20135793.","journal-title":"IEEE Trans. Image Process."},{"key":"2605_CR79","doi-asserted-by":"crossref","unstructured":"Yang, J., Dong, X., Liu, L., Zhang, C., Shen, J., & Yu, D. (2022). Recurring the transformer for video action recognition. Cvpr (pp. 14063\u201314073).","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"2605_CR80","doi-asserted-by":"crossref","unstructured":"Yang, S., Guo, S., Zhao, J., & Shen, F. (2024). Investigating the effectiveness of data augmentation from similarity and diversity: An empirical study. Pattern Recognition,148, Article 110204.","DOI":"10.1016\/j.patcog.2023.110204"},{"issue":"10","key":"2605_CR81","doi-asserted-by":"publisher","first-page":"2349","DOI":"10.1007\/s11263-022-01649-x","volume":"130","author":"N Yudistira","year":"2022","unstructured":"Yudistira, N., Kavitha, M. S., & Kurita, T. (2022). Weakly-supervised action localization, and action recognition using global-local attention of 3d cnn. International Journal of Computer Vision,130(10), 2349\u20132363.","journal-title":"International Journal of Computer Vision"},{"key":"2605_CR82","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. Iccv (p.6023-6032).","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2605_CR83","unstructured":"Yun, S., Oh, S.J., Heo, B., Han, D., & Kim, J. (2020). Videomix: Rethinking data augmentation for video classification. arXiv preprintarXiv:2012.03457,"},{"key":"2605_CR84","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization. Iclr."},{"key":"2605_CR85","unstructured":"Zhang, L., Deng, Z., Kawaguchi, K., Ghorbani, A., & Zou, J. (2021). How does mixup help with robustness and generalization? Iclr."},{"key":"2605_CR86","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020). Random erasing data augmentation. Aaai (Vol.\u00a034, pp. 13001\u201313008).","DOI":"10.1609\/aaai.v34i07.7000"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02605-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02605-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02605-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T15:21:28Z","timestamp":1771341688000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02605-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,17]]},"references-count":86,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2605"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02605-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,17]]},"assertion":[{"value":"23 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"65"}}