{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:10:06Z","timestamp":1779880206245,"version":"3.53.1"},"reference-count":74,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973065"],"award-info":[{"award-number":["61973065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20197"],"award-info":[{"award-number":["U20A20197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.image.2026.117558","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:15:04Z","timestamp":1776233704000},"page":"117558","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["BDTSNet: A novel bidirectional two-stream network for video-based human action recognition"],"prefix":"10.1016","volume":"146","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7943-7411","authenticated-orcid":false,"given":"Chuanjiang","family":"Leng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengdong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ange","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hexiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.image.2026.117558_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2023.108713","article-title":"A review of video action recognition based on 3d convolution","volume":"108","author":"Huang","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.image.2026.117558_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2021.103344","article-title":"Augmented two stream network for robust action recognition adaptive to various action videos","volume":"81","author":"Leng","year":"2021","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.image.2026.117558_b3","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1109\/TCSVT.2021.3077512","article-title":"Spatiotemporal multimodal learning with 3d cnns for video action recognition","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117558_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2022.108112","article-title":"Adaptive 2d skeleton deformation based on view agnostic network for action recognition","volume":"102","author":"Dong","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.image.2026.117558_b5","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.neucom.2020.05.118","article-title":"DB-LSTM: Densely-connected bi-directional lstm for human action recognition","volume":"444","author":"He","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.image.2026.117558_b6","article-title":"Spatio-temporal adaptive network with bidirectional temporal difference for action recognition","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117558_b7","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","article-title":"Videolstm convolves, attends and flows for action recognition","volume":"166","author":"Li","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.image.2026.117558_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111074","article-title":"Exploring incomplete decoupling modeling with window and cross-window mechanism for skeleton-based action recognition","volume":"281","author":"Li","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.image.2026.117558_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2024.109633","article-title":"Enhancing skeleton-based action recognition using a knowledge-driven shift graph convolutional network","volume":"120","author":"Roy","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.image.2026.117558_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2023.108844","article-title":"Human action recognition in complex live videos using graph convolutional network","volume":"110","author":"Bharathi","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.image.2026.117558_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2023.108846","article-title":"Multiple temporal scale aggregation graph convolutional network for skeleton-based action recognition","volume":"110","author":"Li","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.image.2026.117558_b12","doi-asserted-by":"crossref","unstructured":"L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, L. Van Gool, Temporal segment networks: Towards good practices for deep action recognition, in: European Conference on Computer Vision, 2016, pp. 20\u201336.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"10.1016\/j.image.2026.117558_b13","series-title":"Computer Vision\u2013ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, (2018), Revised Selected Papers, Part III 14","first-page":"363","article-title":"Hidden two-stream convolutional networks for action recognition","author":"Zhu","year":"2019"},{"key":"10.1016\/j.image.2026.117558_b14","doi-asserted-by":"crossref","unstructured":"D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri, Learning spatiotemporal features with 3d convolutional networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 4489\u20134497.","DOI":"10.1109\/ICCV.2015.510"},{"key":"10.1016\/j.image.2026.117558_b15","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","article-title":"Long-term temporal convolutions for action recognition","volume":"40","author":"Varol","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2026.117558_b16","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, (2020), Proceedings, Part XVI 16","first-page":"154","article-title":"Temporal aggregate representations for long-range video understanding","author":"Sener","year":"2020"},{"key":"10.1016\/j.image.2026.117558_b17","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, H. Fan, J. Malik, K. He, Slowfast networks for video recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6202\u20136211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10.1016\/j.image.2026.117558_b18","doi-asserted-by":"crossref","first-page":"2965","DOI":"10.1007\/s11263-021-01508-1","article-title":"A coarse-to-fine framework for resource efficient video recognition","volume":"129","author":"Wu","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2026.117558_b19","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2026.117558_b20","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo vadis, action recognition? a new model and the kinetics dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.image.2026.117558_b21","doi-asserted-by":"crossref","unstructured":"Y. Wang, Y. Xiao, F. Xiong, W. Jiang, Z. Cao, J.T. Zhou, J. Yuan, 3dv: 3d dynamic voxel for action recognition in depth video, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 511\u2013520.","DOI":"10.1109\/CVPR42600.2020.00059"},{"key":"10.1016\/j.image.2026.117558_b22","doi-asserted-by":"crossref","unstructured":"X. Li, C. Liu, B. Shuai, Y. Zhu, H. Chen, J. Tighe, Nuta: Non-uniform temporal aggregation for action recognition, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3683\u20133692.","DOI":"10.1109\/WACV51458.2022.00090"},{"key":"10.1016\/j.image.2026.117558_b23","doi-asserted-by":"crossref","unstructured":"H. Kim, M. Jain, J.T. Lee, S. Yun, F. Porikli, Efficient action recognition via dynamic knowledge propagation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13719\u201313728.","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"10.1016\/j.image.2026.117558_b24","doi-asserted-by":"crossref","unstructured":"L. Shi, Y. Zhang, J. Cheng, H. Lu, Adasgn: Adapting joint number and model size for efficient skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13413\u201313422.","DOI":"10.1109\/ICCV48922.2021.01316"},{"key":"10.1016\/j.image.2026.117558_b25","series-title":"Towards good practices for very deep two-stream convnets","author":"Wang","year":"2015"},{"key":"10.1016\/j.image.2026.117558_b26","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, A. Pinz, A. Zisserman, Convolutional two-stream network fusion for video action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1933\u20131941.","DOI":"10.1109\/CVPR.2016.213"},{"key":"10.1016\/j.image.2026.117558_b27","first-page":"8247","article-title":"Attention-aware sampling via deep reinforcement learning for action recognition","volume":"33","author":"Dong","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.image.2026.117558_b28","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.ins.2020.04.030","article-title":"Blind quality assessment for image superresolution using deep two-stream convolutional networks","volume":"528","author":"Zhou","year":"2020","journal-title":"Inform. Sci."},{"key":"10.1016\/j.image.2026.117558_b29","doi-asserted-by":"crossref","first-page":"3946","DOI":"10.1109\/TIP.2019.2902831","article-title":"Dual-stream interactive networks for no-reference stereoscopic image quality assessment","volume":"28","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117558_b30","doi-asserted-by":"crossref","unstructured":"W. Wu, D. He, X. Tan, S. Chen, S. Wen, Multi-agent reinforcement learning based frame sampling for effective untrimmed video recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6222\u20136231.","DOI":"10.1109\/ICCV.2019.00632"},{"key":"10.1016\/j.image.2026.117558_b31","doi-asserted-by":"crossref","unstructured":"J. Lin, C. Gan, S. Han, Tsm: Temporal shift module for efficient video understanding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 7083\u20137093.","DOI":"10.1109\/ICCV.2019.00718"},{"key":"10.1016\/j.image.2026.117558_b32","doi-asserted-by":"crossref","unstructured":"B. Zhou, A. Andonian, A. Oliva, A. Torralba, Temporal relational reasoning in videos, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 803\u2013818.","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"10.1016\/j.image.2026.117558_b33","series-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","author":"Meng","year":"2021"},{"key":"10.1016\/j.image.2026.117558_b34","series-title":"Temporal 3d convnets: New architecture and transfer learning for video classification","author":"Diba","year":"2017"},{"key":"10.1016\/j.image.2026.117558_b35","doi-asserted-by":"crossref","unstructured":"K. Hara, H. Kataoka, Y. Satoh, Learning spatio-temporal features with 3d residual networks for action recognition, in: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 3154\u20133160.","DOI":"10.1109\/ICCVW.2017.373"},{"key":"10.1016\/j.image.2026.117558_b36","doi-asserted-by":"crossref","unstructured":"Z. Qiu, T. Yao, T. Mei, Learning spatio-temporal representation with pseudo-3d residual networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5533\u20135541.","DOI":"10.1109\/ICCV.2017.590"},{"key":"10.1016\/j.image.2026.117558_b37","doi-asserted-by":"crossref","unstructured":"D. Tran, H. Wang, L. Torresani, J. Ray, Y. LeCun, M. Paluri, A closer look at spatiotemporal convolutions for action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6450\u20136459.","DOI":"10.1109\/CVPR.2018.00675"},{"key":"10.1016\/j.image.2026.117558_b38","unstructured":"S. Xie, C. Sun, J. Huang, Z. Tu, K. Murphy, Rethinking spatiotemporal feature learning for video understanding, 1 (2017) 5. arXiv preprint arXiv:1712.04851."},{"key":"10.1016\/j.image.2026.117558_b39","doi-asserted-by":"crossref","unstructured":"C. Li, Q. Zhong, D. Xie, S. Pu, Collaborative spatiotemporal feature learning for video action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7872\u20137881.","DOI":"10.1109\/CVPR.2019.00806"},{"key":"10.1016\/j.image.2026.117558_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2020.102380","article-title":"Vdarn: Video disentangling attentive relation network for few-shot and zero-shot action recognition","volume":"113","author":"Su","year":"2021","journal-title":"Ad Hoc Netw."},{"key":"10.1016\/j.image.2026.117558_b41","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1109\/TMM.2023.3264847","article-title":"Energy-based temporal summarized attentive network for zero-shot action recognition","volume":"25","author":"Qi","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.image.2026.117558_b42","doi-asserted-by":"crossref","unstructured":"H. Zhang, M.C. Leong, L. Li, W. Lin, Pevl: Pose-enhanced vision-language model for fine-grained human action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18857\u201318867.","DOI":"10.1109\/CVPR52733.2024.01784"},{"key":"10.1016\/j.image.2026.117558_b43","doi-asserted-by":"crossref","unstructured":"J. Chalk, J. Huh, E. Kazakos, A. Zisserman, D. Damen, Tim: A time interval machine for audio-visual action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18153\u201318163.","DOI":"10.1109\/CVPR52733.2024.01719"},{"key":"10.1016\/j.image.2026.117558_b44","doi-asserted-by":"crossref","unstructured":"M. Khan, J. Ahmad, A. El Saddik, W. Gueaieb, G. De Masi, F. Karray, Drone-hat: Hybrid attention transformer for complex action recognition in drone surveillance videos, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 4713\u20134722.","DOI":"10.1109\/CVPRW63382.2024.00474"},{"key":"10.1016\/j.image.2026.117558_b45","doi-asserted-by":"crossref","unstructured":"J. Donahue, L. Anne Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, T. Darrell, Long-term recurrent convolutional networks for visual recognition and description, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 2625\u20132634.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10.1016\/j.image.2026.117558_b46","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.image.2026.117558_b47","doi-asserted-by":"crossref","unstructured":"Z. Wu, C. Xiong, C.Y. Ma, R. Socher, L.S. Davis, Adaframe: Adaptive frame selection for fast video recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1278\u20131287.","DOI":"10.1109\/CVPR.2019.00137"},{"key":"10.1016\/j.image.2026.117558_b48","doi-asserted-by":"crossref","unstructured":"W. Zhu, J. Hu, G. Sun, X. Cao, Y. Qiao, A key volume mining deep framework for action recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1991\u20131999.","DOI":"10.1109\/CVPR.2016.219"},{"key":"10.1016\/j.image.2026.117558_b49","doi-asserted-by":"crossref","unstructured":"B. Korbar, D. Tran, L. Torresani, Scsampler: Sampling salient clips from video for efficient action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6232\u20136242.","DOI":"10.1109\/ICCV.2019.00633"},{"key":"10.1016\/j.image.2026.117558_b50","doi-asserted-by":"crossref","first-page":"2971","DOI":"10.1007\/s00371-021-02167-6","article-title":"Human action recognition method based on historical point cloud trajectory characteristics","volume":"38","author":"Li","year":"2022","journal-title":"Vis. Comput."},{"key":"10.1016\/j.image.2026.117558_b51","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, (2020), Proceedings, Part VII 16","first-page":"86","article-title":"Ar-net: Adaptive frame resolution for efficient action recognition","author":"Meng","year":"2020"},{"key":"10.1016\/j.image.2026.117558_b52","series-title":"2024 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Deep bi-directional attention network for image super-resolution quality assessment","author":"Li","year":"2024"},{"key":"10.1016\/j.image.2026.117558_b53","series-title":"IOP Conference Series: Materials Science and Engineering","article-title":"I3D-LSTM: A new model for human action recognition","volume":"Vol. 569","author":"Wang","year":"2019"},{"key":"10.1016\/j.image.2026.117558_b54","doi-asserted-by":"crossref","unstructured":"S.N. Gowda, M. Rohrbach, L. Sevilla-Lara, Smart frame selection for action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 1451\u20131459.","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"10.1016\/j.image.2026.117558_b55","doi-asserted-by":"crossref","unstructured":"H. Li, C. Wang, S. Yu, C. Tao, Action recognition with non-uniform key frame selector, in: Proceedings of the 2023 5th International Conference on Image Processing and Machine Vision, 2023, pp. 24\u201328.","DOI":"10.1145\/3582177.3582182"},{"key":"10.1016\/j.image.2026.117558_b56","doi-asserted-by":"crossref","unstructured":"M. Zhao, Y. Yu, X. Wang, L. Yang, D. Niu, Search-map-search: a frame selection paradigm for action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10627\u201310636.","DOI":"10.1109\/CVPR52729.2023.01024"},{"key":"10.1016\/j.image.2026.117558_b57","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2019.115731","article-title":"Correlation net: Spatiotemporal multimodal deep learning for action recognition","volume":"82","author":"Yudistira","year":"2020","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2026.117558_b58","doi-asserted-by":"crossref","first-page":"3097","DOI":"10.1049\/ipr2.12541","article-title":"Video-based action recognition using spurious-3d residual attention networks","volume":"16","author":"Chen","year":"2022","journal-title":"IET Image Process."},{"key":"10.1016\/j.image.2026.117558_b59","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1049\/iet-ipr.2019.0963","article-title":"Dual attention convolutional network for action recognition","volume":"14","author":"Li","year":"2020","journal-title":"IET Image Process."},{"key":"10.1016\/j.image.2026.117558_b60","doi-asserted-by":"crossref","unstructured":"L. Wang, Z. Tong, B. Ji, G. Wu, Tdn: Temporal difference networks for efficient action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 1895\u20131904.","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"10.1016\/j.image.2026.117558_b61","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.3390\/s23031707","article-title":"Two-level attention module based on spurious-3d residual networks for human action recognition","volume":"23","author":"Chen","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.image.2026.117558_b62","article-title":"Advancing human action recognition: A hybrid approach using attention-based lstm and 3d cnn","volume":"21","author":"Saoudi","year":"2023","journal-title":"Sci. Afr."},{"key":"10.1016\/j.image.2026.117558_b63","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/TCSVT.2018.2830102","article-title":"Semantic cues enhanced multimodality multistream cnn for action recognition","volume":"29","author":"Tu","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117558_b64","doi-asserted-by":"crossref","unstructured":"Z. Shou, X. Lin, Y. Kalantidis, L. Sevilla-Lara, M. Rohrbach, S.F. Chang, Z. Yan, DMC-Net: Generating discriminative motion cues for fast compressed video action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1268\u20131277.","DOI":"10.1109\/CVPR.2019.00136"},{"key":"10.1016\/j.image.2026.117558_b65","doi-asserted-by":"crossref","first-page":"2799","DOI":"10.1109\/TIP.2018.2890749","article-title":"Action-stage emphasized spatiotemporal vlad for video action recognition","volume":"28","author":"Tu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2026.117558_b66","series-title":"2020 IEEE International Conference on Image Processing","first-page":"2216","article-title":"Bubblenet: a disperse recurrent structure to recognize activities","author":"Lo","year":"2020"},{"key":"10.1016\/j.image.2026.117558_b67","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1109\/TCSVT.2021.3070688","article-title":"Factornet: holistic actor, object, and scene factorization for action recognition in videos","volume":"32","author":"Nigam","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117558_b68","doi-asserted-by":"crossref","unstructured":"Y. Zhang, X. Li, C. Liu, B. Shuai, Y. Zhu, B. Brattoli, H. Chen, I. Marsic, J. Tighe, VidTr: Video transformer without convolutions, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13577\u201313587.","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"10.1016\/j.image.2026.117558_b69","doi-asserted-by":"crossref","unstructured":"A. Srivastava, O. Dutta, J. Gupta, S. Agarwal, P. AP, A variational information bottleneck based method to compress sequential networks for human action recognition, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 2745\u20132754.","DOI":"10.1109\/WACV48630.2021.00279"},{"key":"10.1016\/j.image.2026.117558_b70","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.image.2026.117558_b71","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1109\/TMM.2021.3057503","article-title":"Temporal cross-layer correlation mining for action recognition","volume":"24","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.image.2026.117558_b72","doi-asserted-by":"crossref","unstructured":"G. Huang, A.G. Bors, Busy-quiet video disentangling for video classification, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 1341\u20131350.","DOI":"10.1109\/WACV51458.2022.00083"},{"key":"10.1016\/j.image.2026.117558_b73","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2023.116940","article-title":"Multi-level channel attention excitation network for human action recognition in videos","volume":"114","author":"Wu","year":"2023","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2026.117558_b74","doi-asserted-by":"crossref","first-page":"4133","DOI":"10.1007\/s00371-023-03073-9","article-title":"Bdnet: a method based on forward and backward convolutional networks for action recognition in videos","volume":"40","author":"Leng","year":"2024","journal-title":"Vis. Comput."}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526000810?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526000810?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:48:06Z","timestamp":1779878886000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596526000810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":74,"alternative-id":["S0923596526000810"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2026.117558","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BDTSNet: A novel bidirectional two-stream network for video-based human action recognition","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2026.117558","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"117558"}}