{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:47:30Z","timestamp":1774540050103,"version":"3.50.1"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03478-0","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T19:01:33Z","timestamp":1718305293000},"page":"1719-1731","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Differential motion attention network for efficient action recognition"],"prefix":"10.1007","volume":"41","author":[{"given":"Caifeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangjie","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,13]]},"reference":[{"issue":"7","key":"3478_CR1","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"B Sheng","year":"2021","unstructured":"Sheng, B., Li, P., Ali, R., Chen, C.P.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662\u20136675 (2021)","journal-title":"IEEE Trans. Cybern."},{"issue":"11","key":"3478_CR2","doi-asserted-by":"publisher","first-page":"7885","DOI":"10.1109\/TPAMI.2021.3115815","volume":"44","author":"X Lu","year":"2021","unstructured":"Lu, X., Wang, W., Shen, J., Crandall, D.J., Van Gool, L.: Segmenting objects from relational visual data. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7885\u20137897 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3478_CR3","doi-asserted-by":"crossref","unstructured":"Qin, Z., Lu, X., Liu, D., Nie, X., Yin, Y., Shen, J., Loui, A.C.: Reformulating graph kernels for self-supervised space-time correspondence learning. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3328485"},{"key":"3478_CR4","doi-asserted-by":"crossref","unstructured":"Wu, P., Lu, X., Shen, J., Yin, Y.: Clip fusion with bi-level optimization for human mesh reconstruction from monocular videos. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 105\u2013115 (2023)","DOI":"10.1145\/3581783.3611978"},{"issue":"5","key":"3478_CR5","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1109\/JAS.2023.123456","volume":"10","author":"Z Qin","year":"2023","unstructured":"Qin, Z., Lu, X., Nie, X., Liu, D., Yin, Y., Wang, W.: Coarse-to-fine video instance segmentation with factorized conditional appearance flows. IEEE\/CAA J. Automatica Sinica 10(5), 1192\u20131208 (2023)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"3478_CR6","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"3478_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: 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 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"3478_CR8","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"3478_CR9","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"3478_CR10","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arXiv:1712.04851 1(2), 5 (2017)"},{"key":"3478_CR11","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"3478_CR12","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"3478_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: Stm: Spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"3478_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: Temporal excitation and aggregation for action recognition. arXiv preprint arXiv:2004.01398 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"3478_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., Kahou, S.E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV, vol. 1, p. 5 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"3478_CR16","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"issue":"2\u20133","key":"3478_CR17","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vision"},{"key":"3478_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"3478_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van\u00a0Gool, L.: Temporal segment networks: Towards good practices for deep action recognition. In: European Conference on Computer Vision, pp. 20\u201336 (2016). Springer","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"3478_CR20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"3478_CR21","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: A fast and robust motion representation for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1390\u20131399 (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"3478_CR22","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: Mars: Motion-augmented rgb stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"3478_CR23","unstructured":"Alfasly, S., Chui, C.K., Jiang, Q., Lu, J., Xu, C.: An effective video transformer with synchronized spatiotemporal and spatial self-attention for action recognition. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"3478_CR24","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"3478_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"3478_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3180420","volume":"14","author":"Y Su","year":"2018","unstructured":"Su, Y., Feng, Z., Zhang, J., Peng, W., Xing, M.: Sequential articulated motion reconstruction from a monocular image sequence. ACM Trans. Multimed. Comput. Commun. Appl. 14, 1\u201321 (2018)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"3478_CR27","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5512\u20135521 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"3478_CR28","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"3478_CR29","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Gate-shift networks for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1102\u20131111 (2020)","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"3478_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., Li, J., Huang, F., Lu, T.: Teinet: Towards an efficient architecture for video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"3478_CR31","doi-asserted-by":"crossref","unstructured":"Shao, H., Qian, S., Liu, Y.: Temporal interlacing network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11966\u201311973 (2020)","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"3478_CR32","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: Tdn: Temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"3478_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Hu, Q., Gao, Z., Li, P., Hu, Q.: Ams-net: Modeling adaptive multi-granularity spatio-temporal cues for video action recognition. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3321141"},{"key":"3478_CR34","unstructured":"Lu, T., Yang, Q., Min, F., Zhang, Y.: Action recognition based on adaptive region perception. Neural Comput. Appl. pp. 1\u201317 (2023)"},{"key":"3478_CR35","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, H.G., Choi, D.H., Kim, H.-I., Ro, Y.M.: Video prediction recalling long-term motion context via memory alignment learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3054\u20133063 (2021)","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"3478_CR36","first-page":"12493","volume":"34","author":"M Patrick","year":"2021","unstructured":"Patrick, M., Campbell, D., Asano, Y., Misra, I., Metze, F., Feichtenhofer, C., Vedaldi, A., Henriques, J.F.: Keeping your eye on the ball: Trajectory attention in video transformers. Adv. Neural. Inf. Process. Syst. 34, 12493\u201312506 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3478_CR37","doi-asserted-by":"crossref","unstructured":"Kim, B., Chang, H.J., Kim, J., Choi, J.Y.: Global-local motion transformer for unsupervised skeleton-based action learning. In: European Conference on Computer Vision, pp. 209\u2013225 (2022). Springer","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"3478_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., Smolic, A.: Action-net: Multipath excitation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13214\u201313223 (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"3478_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2020.102380","volume":"113","author":"Y Su","year":"2021","unstructured":"Su, Y., Xing, M., An, S., Peng, W., Feng, Z.: Vdarn: Video disentangling attentive relation network for few-shot and zero-shot action recognition. Ad Hoc Netw. 113, 102380 (2021)","journal-title":"Ad Hoc Netw."},{"issue":"6","key":"3478_CR40","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1109\/TPAMI.2021.3053765","volume":"44","author":"M Li","year":"2021","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3316\u20133333 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3478_CR41","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: Unsupervised video object segmentation with co-attention siamese networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3623\u20133632 (2019)","DOI":"10.1109\/CVPR.2019.00374"},{"key":"3478_CR42","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: Motionsqueeze: Neural motion feature learning for video understanding. In: European Conference on Computer Vision, pp. 345\u2013362 (2020). Springer","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"3478_CR43","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1016\/j.patrec.2018.08.002","volume":"112","author":"LA Lim","year":"2018","unstructured":"Lim, L.A., Keles, H.Y.: Foreground segmentation using convolutional neural networks for multiscale feature encoding. Pattern Recogn. Lett. 112, 256\u2013262 (2018)","journal-title":"Pattern Recogn. Lett."},{"key":"3478_CR44","unstructured":"Singh, B., Najibi, M., Davis, L.S.: Sniper: Efficient multi-scale training. arXiv preprint arXiv:1805.09300 (2018)"},{"key":"3478_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 143\u2013152 (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"3478_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3478_CR47","doi-asserted-by":"publisher","first-page":"7313","DOI":"10.1007\/s11042-020-09643-6","volume":"80","author":"C Liu","year":"2021","unstructured":"Liu, C., Feng, L., Liu, G., Wang, H., Liu, S.: Bottom-up broadcast neural network for music genre classification. Multimed. Tools Appl. 80, 7313\u20137331 (2021)","journal-title":"Multimed. Tools Appl."},{"key":"3478_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., Yao, M., Jiang, G., Mi, Z., Fu, X.: Graph-collaborated auto-encoder hashing for multiview binary clustering. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3239033"},{"key":"3478_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., Jiang, G., Peng, J., Deng, R., Fu, X.: Towards adaptive consensus graph: multi-view clustering via graph collaboration. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3212270"},{"key":"3478_CR50","doi-asserted-by":"publisher","first-page":"3828","DOI":"10.1109\/TMM.2020.3032023","volume":"23","author":"H Wang","year":"2020","unstructured":"Wang, H., Wang, Y., Zhang, Z., Fu, X., Zhuo, L., Xu, M., Wang, M.: Kernelized multiview subspace analysis by self-weighted learning. IEEE Trans. Multimed. 23, 3828\u20133840 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"3478_CR51","doi-asserted-by":"crossref","unstructured":"Hu, L., Liu, S., Feng, W.: Skeleton-based action recognition with local dynamic spatial-temporal aggregation. Exp. Syst. Appl. 120683 (2023)","DOI":"10.1016\/j.eswa.2023.120683"},{"issue":"8","key":"3478_CR52","doi-asserted-by":"publisher","first-page":"3417","DOI":"10.1007\/s00371-023-02979-8","volume":"39","author":"L Gao","year":"2023","unstructured":"Gao, L., Hu, L., Lyu, F., Zhu, L., Wan, L., Pun, C.-M., Feng, W.: Difference-guided multi-scale spatial-temporal representation for sign language recognition. Vis. Comput. 39(8), 3417\u20133428 (2023)","journal-title":"Vis. Comput."},{"key":"3478_CR53","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"3478_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3478_CR55","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3478_CR56","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3478_CR57","doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Self-emphasizing network for continuous sign language recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 854\u2013862 (2023)","DOI":"10.1609\/aaai.v37i1.25164"},{"key":"3478_CR58","doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Continuous sign language recognition with correlation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2529\u20132539 (2023)","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"3478_CR59","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. (2021)"},{"key":"3478_CR60","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: Mngnas: Distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3293885"},{"key":"3478_CR61","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. pp. 8024\u20138035 (2019)"},{"key":"3478_CR62","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3478_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"3478_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 803\u2013818 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"3478_CR65","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 399\u2013417 (2018)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"3478_CR66","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xu, C., Hui, L., Lu, C., Tao, D.: Approximated bilinear modules for temporal modeling. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3494\u20133503 (2019)","DOI":"10.1109\/ICCV.2019.00359"},{"key":"3478_CR67","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Trajectory convolution for action recognition. In: Advances in Neural Information Processing Systems, pp. 2204\u20132215 (2018)"},{"key":"3478_CR68","doi-asserted-by":"crossref","unstructured":"Wang, H., Tran, D., Torresani, L., Feiszli, M.: Video modeling with correlation networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 352\u2013361 (2020)","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"3478_CR69","unstructured":"Zhang, S., Guo, S., Huang, W., Scott, M.R., Wang, L.: V4d: 4d convolutional neural networks for video-level representation learning. arXiv preprint arXiv:2002.07442 (2020)"},{"key":"3478_CR70","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Zhou, Z., Qiao, Y.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"3478_CR71","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: Tam: Temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13708\u201313718 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"3478_CR72","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, C., Shuai, B., Zhu, Y., Chen, H., Tighe, J.: Nuta: Non-uniform temporal aggregation for action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3683\u20133692 (2022)","DOI":"10.1109\/WACV51458.2022.00090"},{"key":"3478_CR73","unstructured":"Fan, Q., Panda, R., et al.: Can an image classifier suffice for action recognition? Proceedings of the International Conference on Learning Representations (2022)"},{"key":"3478_CR74","unstructured":"Huang, Z., Zhang, S., Pan, L., Qing, Z., Tang, M., Liu, Z., Ang\u00a0Jr, M.H.: Tada! temporally-adaptive convolutions for video understanding. Proceedings of the International Conference on Learning Representations (2022)"},{"key":"3478_CR75","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"3478_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, J., Fu, Z., Huang, Q., Liu, Q., Wang, Y.: Lgnet: A local-global network for action recognition and beyond. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3189253"},{"key":"3478_CR77","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03478-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03478-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03478-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T14:54:26Z","timestamp":1739372066000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03478-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,13]]},"references-count":77,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3478"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03478-0","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,13]]},"assertion":[{"value":"9 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}