{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:22:01Z","timestamp":1774448521661,"version":"3.50.1"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101524"],"award-info":[{"award-number":["62101524"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11263-024-02154-z","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T07:02:38Z","timestamp":1719471758000},"page":"5820-5840","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diansong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"2154_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. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 6836\u20136846).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"2154_CR2","unstructured":"Bertasius, G., Wang, H., & Torresani, L. (2021). Is space-time attention all you need for video understanding? Icml (Vol. 2, p. 4)."},{"key":"2154_CR3","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":"2154_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., & Ho, C. M. (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":"2154_CR5","unstructured":"Cordonnier, J.-B., Loukas, A., & Jaggi, M. (2019). On the relationship between self-attention and convolutional layers. arXiv:1911.03584"},{"issue":"1","key":"2154_CR6","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TAFFC.2016.2573832","volume":"9","author":"AK Davison","year":"2016","unstructured":"Davison, A. K., Lansley, C., Costen, N., Tan, K., & Yap, M. H. (2016). Samm: A spontaneous microfacial movement dataset. IEEE Transactions on Affective Computing, 9(1), 116\u2013129.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"2154_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"2154_CR8","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M. L., Morcos, A. S., Biroli, G., & Sagun, L. (2021). Convit: Improving vision transformers with soft convolutional inductive biases. In International conference on machine learning (pp. 2286\u20132296).","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"2154_CR9","first-page":"19594","volume":"34","author":"A Bulat","year":"2021","unstructured":"Bulat, A., et al. (2021). Space-time mixing attention for video transformer. Advances in Neural Information Processing Systems, 34, 19594\u201319607.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2154_CR10","unstructured":"Fan, H., Li, Y., Xiong, B., Lo, W.-Y., & Feichtenhofer, C. (2020). Pyslowfast. https:\/\/github.com\/facebookresearch\/slowfast"},{"key":"2154_CR11","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":"2154_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020). X3d: Expanding architectures for efficient video recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 203\u2013213).","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2154_CR13","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":"2154_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In Proceedings of the ieee international conference on computer vision (pp. 1440\u20131448).","DOI":"10.1109\/ICCV.2015.169"},{"key":"2154_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., et al. (2017). The \u201dsomething something\u201d 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":"2154_CR16","doi-asserted-by":"crossref","unstructured":"Gu, C., Sun, C., Ross, D. A., Vondrick, C., Pantofaru, C., Li, Y., et al. (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"},{"issue":"10","key":"2154_CR17","doi-asserted-by":"publisher","first-page":"7120","DOI":"10.1109\/TCSVT.2022.3169842","volume":"32","author":"Y Hao","year":"2022","unstructured":"Hao, Y., Wang, S., Cao, P., Gao, X., Xu, T., Wu, J., & He, X. (2022). Attention in attention: Modeling context correlation for efficient video classification. IEEE Transactions on Circuits and Systems for Video Technology, 32(10), 7120\u20137132.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2154_CR18","doi-asserted-by":"crossref","unstructured":"Hao, Y., Zhang, H., Ngo, C.-W., & He, X. (2022). Group contextualization for video recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 928\u2013938).","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"2154_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the ieee international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2154_CR20","doi-asserted-by":"crossref","unstructured":"Herzig, R., Ben-Avraham, E., Mangalam, K., Bar, A., Chechik, G., Rohrbach, A., & Globerson, A. (2022). Object-region video transformers. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 3148\u20133159).","DOI":"10.1109\/CVPR52688.2022.00315"},{"issue":"1","key":"2154_CR21","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TPAMI.2022.3145427","volume":"45","author":"Q Hou","year":"2022","unstructured":"Hou, Q., Jiang, Z., Yuan, L., Cheng, M.-M., Yan, S., & Feng, J. (2022). Vision permutator: A permutable mlp-like architecture for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 1328\u20131334.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2154_CR22","unstructured":"Islam, M. A., Kowal, M., Jia, S., Derpanis, K. G., & Bruce, N. D. (2021a). Global pooling, more than meets the eye: Position information is encoded channel-wise in cnns. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 793\u2013801)."},{"key":"2154_CR23","unstructured":"Islam, M. A., Kowal, M., Jia, S., Derpanis, K. G., & Bruce, N. D. (2021b). Position, padding and predictions: A deeper look at position information in cnns. arXiv:2101.12322"},{"key":"2154_CR24","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":"2154_CR25","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., et al. (2017). The kinetics human action video dataset. arXiv:1705.06950"},{"key":"2154_CR26","unstructured":"Kayhan, O. S., & Gemert, J. C. V. (2020). On translation invariance in cnns: Convolutional layers can exploit absolute spatial location. InProceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 14274\u201314285)."},{"key":"2154_CR27","doi-asserted-by":"crossref","unstructured":"Khor, H.-Q., See, J., Liong, S.-T., Phan, R. C., & Lin, W. (2019). Dual-stream shallow networks for facial micro-expression recognition. In 2019 ieee international conference on image processing (icip) (pp. 36\u201340).","DOI":"10.1109\/ICIP.2019.8802965"},{"key":"2154_CR28","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., & Cho, M. (2020). Motionsqueeze: Neural motion feature learning for video understanding. In Computer vision\u2014eccv 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part xvi 16 (pp. 345\u2013362).","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"2154_CR29","doi-asserted-by":"crossref","unstructured":"Li, H., Sui, M., Zhu, Z., & Zhao, F. (2022). Mmnet: Muscle motion-guided network for micro-expression recognition. arXiv:2201.05297","DOI":"10.24963\/ijcai.2022\/150"},{"issue":"3","key":"2154_CR30","first-page":"2782","volume":"45","author":"J Li","year":"2022","unstructured":"Li, J., Dong, Z., Lu, S., Wang, S.-J., Yan, W.-J., Ma, Y., & Fu, X. (2022). Cas (me) 3: A third generation facial spontaneous micro-expression database with depth information and high ecological validity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 2782\u20132800.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2154_CR31","unstructured":"Li, K., Li, X., Wang, Y., Wang, J., & Qiao, Y. (2021). Ct-net: Channel tensorization network for video classification. arXiv:2106.01603"},{"key":"2154_CR32","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., et al. (2023). Uniformer: Unifying convolution and self-attention for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"2154_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Pfister, T., Huang, X., Zhao, G., & Pietik\u00e4inen, M. (2013). A spontaneous micro-expression database: Inducement, collection and baseline. In 2013 10th ieee international conference and workshops on automatic face and gesture recognition (fg) (pp. 1\u20136).","DOI":"10.1109\/FG.2013.6553717"},{"key":"2154_CR34","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Zhou, Z., & Qiao, Y. (2020). Smallbignet: Integrating core and contextual views for video classification. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 1092\u20131101).","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"2154_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., & Wang, L. (2020). Tea: Temporal excitation and aggregation for action recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 909\u2013918).","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"2154_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., & Vasconcelos, N. (2018). Resound: Towards action recognition without representation bias. In Proceedings of the European conference on computer vision (eccv) (pp. 513\u2013528).","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"2154_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., & Rehg, J.M. (2018). In the eye of beholder: Joint learning of gaze and actions in first person video. In Proceedings of the european conference on computer vision (eccv) (pp. 619\u2013635).","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"2154_CR38","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. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 4804\u20134814).","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"2154_CR39","unstructured":"Lian, D., Yu, Z., Sun, X., & Gao, S. (2021). As-mlp: An axial shifted mlp architecture for vision. arXiv:2107.08391"},{"key":"2154_CR40","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":"2154_CR41","doi-asserted-by":"crossref","unstructured":"Liong, S.-T., Gan, Y. S., See, J., Khor, H.-Q., & Huang, Y.-C. (2019). Shallow triple stream threedimensional cnn (ststnet) for micro-expression recognition. In 2019 14th ieee international conference on automatic face and gesture recognition (fg 2019) (pp. 1\u20135).","DOI":"10.1109\/FG.2019.8756567"},{"key":"2154_CR42","first-page":"9204","volume":"34","author":"H Liu","year":"2021","unstructured":"Liu, H., Dai, Z., So, D., & Le, Q. V. (2021). Pay attention to mlps. Advances in Neural Information Processing Systems, 34, 9204\u20139215.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2154_CR43","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. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2154_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., & Lu, T. (2020). Teinet: Towards an efficient architecture for video recognition. In Proceedings of the aaai conference on artificial intelligence (Vol. 34, pp. 11669\u201311676).","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"2154_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 3202\u2013 3211).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2154_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., & Lu, T. (2021). Tam: Temporal adaptive module for video recognition. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 13708\u201313718).","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"2154_CR47","doi-asserted-by":"crossref","unstructured":"Luo, C., & Yuille, A.L. (2019). Grouped spatialtemporal aggregation for efficient action recognition. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 5512\u20135521).","DOI":"10.1109\/ICCV.2019.00561"},{"key":"2154_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen, X.-B., Duong, C.N., Li, X., Gauch, S., Seo, H.-S., & Luu, K. (2023). Micron-bert: Bert-based facial micro-expression recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 1482\u2013 1492).","DOI":"10.1109\/CVPR52729.2023.00149"},{"key":"2154_CR49","first-page":"12493","volume":"34","author":"M Patrick","year":"2021","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. Advances in Neural Information Processing Systems, 34, 12493\u201312506.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2154_CR50","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., & Mei, T. (2017). Learning spatiotemporal 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"},{"key":"2154_CR51","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. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 3062\u20133072).","DOI":"10.1109\/CVPR52688.2022.00307"},{"issue":"1","key":"2154_CR52","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified textto- text transformer. The Journal of Machine Learning Research, 21(1), 5485\u20135551.","journal-title":"The Journal of Machine Learning Research"},{"key":"2154_CR53","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28."},{"key":"2154_CR54","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Gradcam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the ieee international conference on computer vision (pp. 618\u2013626).","DOI":"10.1109\/ICCV.2017.74"},{"key":"2154_CR55","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., & Vaswani, A. (2018). Selfattention with relative position representations. arXiv:1803.02155","DOI":"10.18653\/v1\/N18-2074"},{"key":"2154_CR56","unstructured":"Tan, H., Lei, J., Wolf, T., & Bansal, M. (2021). Vimpac: Video pre-training via masked token prediction and contrastive learning. arXiv:2106.11250"},{"key":"2154_CR57","doi-asserted-by":"crossref","unstructured":"Tan, Y., Hao, Y., He, X., Wei, Y., & Yang, X. (2021). Selective dependency aggregation for action classification. In Proceedings of the 29th acm international conference on multimedia (pp. 592\u2013601).","DOI":"10.1145\/3474085.3475218"},{"key":"2154_CR58","doi-asserted-by":"crossref","unstructured":"Tan, Y., Hao, Y., Zhang, H., Wang, S., & He, X. (2022). Hierarchical hourglass convolutional network for efficient video classification. In Proceedings of the 30th acm international conference on multimedia (pp. 5880\u20135891).","DOI":"10.1145\/3503161.3547841"},{"key":"2154_CR59","first-page":"24261","volume":"34","author":"IO Tolstikhin","year":"2021","unstructured":"Tolstikhin, I. O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., et al. (2021). Mlp-mixer: An all-mlp architecture for vision. Advances in Neural Information Processing Systems, 34, 24261\u201324272.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2154_CR60","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., & Wang, L. (2022). Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems, 35, 10078\u201310093.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2154_CR61","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"},{"key":"2154_CR62","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":"2154_CR63","doi-asserted-by":"crossref","unstructured":"Tu, S., Dai, Q., Wu, Z., Cheng, Z.-Q., Hu, H., & Jiang, Y.-G. (2023). Implicit temporal modeling with learnable alignment for video recognition. In Proceedings of the ieee\/cvf international conference on computer vision (pp. 19936\u201319947).","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"2154_CR64","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30."},{"key":"2154_CR65","doi-asserted-by":"crossref","unstructured":"Wang, J., & Torresani, L. (2022). Deformable video transformer. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 14053\u201314062).","DOI":"10.1109\/CVPR52688.2022.01366"},{"key":"2154_CR66","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., & Wu, G. (2021). Tdn: Temporal difference networks for efficient action recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 1895\u20131904).","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"2154_CR67","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. Proceedings of the ieee conference on computer vision and pattern recognition (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2154_CR68","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, Y., Zhu, L., & Yang, Y. (2020). Symbiotic attention with privileged information for egocentric action recognition. In Proceedings of the aaai conference on artificial intelligence (Vol. 34, pp. 12249\u201312256).","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"2154_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z., Hao, Y., Gao, X., Zhang, H., Wang, S., Mu, T., & He, X. (2022). Parameterization of crosstoken relations with relative positional encoding for vision mlp. In Proceedings of the 30th acm international conference on multimedia (pp. 6288\u20136299).","DOI":"10.1145\/3503161.3547953"},{"key":"2154_CR70","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., Li, Y., Mangalam, K., Fan, H., Xiong, B., Malik, J., & Feichtenhofer, C. (2022). Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 13587\u201313597).","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"2154_CR71","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. In Proceedings of the european conference on computer vision (eccv) (pp. 305\u2013 321).","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"2154_CR72","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. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 18816\u201318826).","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"2154_CR73","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. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 3333\u20133343).","DOI":"10.1109\/CVPR52688.2022.00333"},{"issue":"1","key":"2154_CR74","doi-asserted-by":"publisher","first-page":"e86041","DOI":"10.1371\/journal.pone.0086041","volume":"9","author":"W-J Yan","year":"2014","unstructured":"Yan, W.-J., Li, X., Wang, S.-J., Zhao, G., Liu, Y. J., Chen, Y.-H., & Fu, X. (2014). Casme ii: An improved spontaneous micro-expression database and the baseline evaluation. PLOS ONE, 9(1), e86041.","journal-title":"PLOS ONE"},{"key":"2154_CR75","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. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 14063\u201314073).","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"2154_CR76","doi-asserted-by":"crossref","unstructured":"Yu, T., Li, X., Cai, Y., Sun, M., & Li, P. (2022). S2-mlp: Spatial-shift mlp architecture for vision. In Proceedings of the ieee\/cvf winter conference on applications of computer vision (pp. 297\u2013306).","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"2154_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., & Zisserman, A. (2021). Temporal query networks for fine-grained video understanding. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 4486\u20134496).","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"2154_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, D. J., Li, K., Wang, Y., Chen, Y., Chandra, S., Qiao, Y., & Shou, M. Z. (2022). Morphmlp: An efficient mlp-like backbone for spatial-temporal representation learning. In Computer vision\u2013eccv 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, proceedings, part xxxv (pp. 230\u2013248).","DOI":"10.1007\/978-3-031-19833-5_14"},{"key":"2154_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cheng, L., Hao, Y., & Ngo, C.-w. (2022). Long-term leap attention, short-term periodic shift for video classification. In Proceedings of the 30th acm international conference on multimedia (pp. 5773\u20135782).","DOI":"10.1145\/3503161.3547908"},{"key":"2154_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., & Ngo, C.-W. (2021). Token shift transformer for video classification. In Proceedings of the 29th acm international conference on multimedia (pp. 917\u2013925).","DOI":"10.1145\/3474085.3475272"},{"key":"2154_CR81","unstructured":"Zhang, S. (2022). Tfcnet: Temporal fully connected networks for static unbiased temporal reasoning. arXiv:2203.05928"},{"issue":"276\u2013289","key":"2154_CR82","first-page":"24","volume":"448","author":"S Zhao","year":"2021","unstructured":"Zhao, S., Tao, H., Zhang, Y., Xu, T., Zhang, K., Hao, Z., & Chen, E. (2021). A two-stage 3d cnn based learning method for spontaneous microexpression recognition. Neurocomputing, 448(276\u2013289), 24.","journal-title":"Neurocomputing"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02154-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02154-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02154-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T10:19:55Z","timestamp":1731665995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02154-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":82,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2154"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02154-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]},"assertion":[{"value":"23 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}