{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T23:10:22Z","timestamp":1783465822433,"version":"3.55.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"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":["62072127"],"award-info":[{"award-number":["62072127"]}],"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":["62002076"],"award-info":[{"award-number":["62002076"]}],"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":["61906049"],"award-info":[{"award-number":["61906049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ience and Technology Program of Guangzhou","award":["202002030131"],"award-info":[{"award-number":["202002030131"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["2019A1515110213"],"award-info":[{"award-number":["2019A1515110213"]}]},{"DOI":"10.13039\/501100018540","name":"Natural Science Foundation of Guangdong Province for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["2020A1515010423"],"award-info":[{"award-number":["2020A1515010423"]}],"id":[{"id":"10.13039\/501100018540","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Netw"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11276-023-03267-y","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T16:02:51Z","timestamp":1677600171000},"page":"5389-5405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A spatiotemporal and motion information extraction network for action recognition"],"prefix":"10.1007","volume":"30","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3480-8780","authenticated-orcid":false,"given":"Xianmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuekai","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuemei","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"3267_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-021-02693-0","author":"T Zhang","year":"2021","unstructured":"Zhang, T. (2021). Application of ai-based real-time gesture recognition and embedded system in the design of english major teaching. Wireless Networks. https:\/\/doi.org\/10.1007\/s11276-021-02693-0","journal-title":"Wireless Networks"},{"key":"3267_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-021-02721-z","author":"Y He","year":"2021","unstructured":"He, Y. (2021). Athlete human behavior recognition based on continuous image deep learning and sensors. Wireless Networks. https:\/\/doi.org\/10.1007\/s11276-021-02721-z","journal-title":"Wireless Networks"},{"key":"3267_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-022-03011-y","author":"H Mittal","year":"2022","unstructured":"Mittal, H., Tripathi, A., Pandey, A., Parameswaran, V., Menon, V., & Pal, R. (2022). A novel fuzzy clustering-based method for human activity recognition in cloud-based industrial iot environment. Wireless Networks. https:\/\/doi.org\/10.1007\/s11276-022-03011-y","journal-title":"Wireless Networks"},{"key":"3267_CR4","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.ins.2020.03.066","volume":"531","author":"T Huang","year":"2020","unstructured":"Huang, T., Chen, Y., Yao, B., Yang, B., Wang, X., & Li, Y. (2020). Adversarial attacks on deep-learning-based radar range profile target recognition. Information Sciences, 531, 159\u2013176.","journal-title":"Information Sciences"},{"key":"3267_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108368","volume":"123","author":"H Yang","year":"2022","unstructured":"Yang, H., Chen, L., Pan, S., Wang, H., & Zhang, P. (2022). Discrete embedding for attributed graphs. Pattern Recognition, 123, 108368.","journal-title":"Pattern Recognition"},{"issue":"7","key":"3267_CR6","doi-asserted-by":"publisher","first-page":"3244","DOI":"10.1109\/TII.2018.2799928","volume":"14","author":"Z Liu","year":"2018","unstructured":"Liu, Z., Wu, Z., Li, T., Li, J., & Shen, C. (2018). Gmm and cnn hybrid method for short utterance speaker recognition. IEEE Transactions on Industrial informatics, 14(7), 3244\u20133252.","journal-title":"IEEE Transactions on Industrial informatics"},{"key":"3267_CR7","doi-asserted-by":"publisher","unstructured":"Liu, X., Shi, H., Chen, H., Yu, Z., Li, X., & Zhao, G (2021). imigue: An identity-free video dataset for micro-gesture understanding and emotion analysis. In 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10626\u2013 10637). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01049","DOI":"10.1109\/CVPR46437.2021.01049"},{"key":"3267_CR8","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.ins.2018.11.046","volume":"479","author":"H Yan","year":"2019","unstructured":"Yan, H., Chen, Z., & Jia, C. (2019). Ssir: Secure similarity image retrieval in iot. Information Sciences, 479, 153\u2013163.","journal-title":"Information Sciences"},{"issue":"6","key":"3267_CR9","first-page":"2996","volume":"18","author":"Y Meng","year":"2020","unstructured":"Meng, Y., Zhu, H., Li, J., Li, J., & Liu, Y. (2020). Liveness detection for voice user interface via wireless signals in iot environment. IEEE Transactions on Dependable and Secure Computing, 18(6), 2996\u20133011.","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"3267_CR10","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.cose.2017.11.012","volume":"76","author":"W Meng","year":"2018","unstructured":"Meng, W., Jiang, L., Wang, Y., Li, J., Zhang, J., & Xiang, Y. (2018). Jfcguard: Detecting juice filming charging attack via processor usage analysis on smartphones. Computers & Security, 76, 252\u2013264.","journal-title":"Computers & Security"},{"key":"3267_CR11","doi-asserted-by":"crossref","unstructured":"Dong, C., Wang, Y., Aldweesh, A., McCorry, P., & van Moorsel, A. (2017). Betrayal, distrust, and rationality: Smart counter-collusion contracts for verifiable cloud computing. In Proceedings of the 2017 ACM SIGSAC conference on computer and communications security (pp. 211\u2013 227).","DOI":"10.1145\/3133956.3134032"},{"key":"3267_CR12","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.ins.2022.04.003","volume":"601","author":"R Hou","year":"2022","unstructured":"Hou, R., Ai, S., Chen, Q., Yan, H., Huang, T., & Chen, K. (2022). Similarity-based integrity protection for deep learning systems. Information Sciences, 601, 255\u2013267.","journal-title":"Information Sciences"},{"key":"3267_CR13","doi-asserted-by":"crossref","unstructured":"Peng, Y., Choi, B., & Xu, J. ( 2021). Graph edit distance learning via modeling optimum matchings with constraints. In IJCAI (pp. 1534\u2013 1540).","DOI":"10.24963\/ijcai.2021\/212"},{"issue":"3","key":"3267_CR14","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1109\/TCE.2007.4341600","volume":"53","author":"R Li","year":"2007","unstructured":"Li, R., Yu, S., & Yang, X. (2007). Efficient spatio-temporal segmentation for extracting moving objects in video sequences. IEEE Transactions on Consumer Electronics, 53(3), 1161\u20131167. https:\/\/doi.org\/10.1109\/TCE.2007.4341600","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"3267_CR15","doi-asserted-by":"crossref","unstructured":"Wu, H., Ma, X., & Li, Y. (2021). Spatiotemporal multimodal learning with 3d cnns for video action recognition. IEEE Transactions on Circuits and Systems for Video Technology, 1\u20131.","DOI":"10.1109\/TCSVT.2021.3077512"},{"issue":"2","key":"3267_CR16","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/TCE.2019.2908986","volume":"65","author":"CN Phyo","year":"2019","unstructured":"Phyo, C. N., Zin, T. T., & Tin, P. (2019). Deep learning for recognizing human activities using motions of skeletal joints. IEEE Transactions on Consumer Electronics, 65(2), 243\u2013252. https:\/\/doi.org\/10.1109\/TCE.2019.2908986","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"3267_CR17","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems (pp. 568\u2013 576)."},{"key":"3267_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2016). Convolutional two-stream network fusion for video action recognition. In 2016 IEEE conference on computer vision and pattern recognition (pp. 1933\u2013 1941).","DOI":"10.1109\/CVPR.2016.213"},{"key":"3267_CR19","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In 2017 IEEE conference on computer vision and pattern recognition (pp. 4724\u2013 4733).","DOI":"10.1109\/CVPR.2017.502"},{"key":"3267_CR20","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 (pp. 305\u2013 321).","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"3267_CR21","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Xiong, Y., & Lin, D. (2018). Recognize actions by disentangling components of dynamics. In 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 6566\u2013 6575)). https:\/\/doi.org\/10.1109\/CVPR.2018.00687","DOI":"10.1109\/CVPR.2018.00687"},{"key":"3267_CR22","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In 2015 IEEE international conference on computer vision (pp. 4489\u2013 4497).","DOI":"10.1109\/ICCV.2015.510"},{"key":"3267_CR23","doi-asserted-by":"crossref","unstructured":"Stroud, J.C., Ross, D.A., Sun, C., Deng, J., & Sukthankar, R. (2020). D3d: Distilled 3d networks for video action recognition. In 2020 IEEE winter conference on applications of computer vision (pp. 614\u2013 623).","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"3267_CR24","first-page":"352","volume":"31","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., & Feng, J. (2018). $$a^{2}$$-nets: Double attention networks. Advances in Neural Information Processing Systems, 31, 352\u2013361.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"3267_CR25","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. ( 2018). Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 6546\u2013 6555).","DOI":"10.1109\/CVPR.2018.00685"},{"key":"3267_CR26","doi-asserted-by":"crossref","unstructured":"Peng, F., Liao, T., & Long, M. (2022). A semi-fragile reversible watermarking for authenticating 3d models in dual domains based on variable direction double modulation. IEEE Transactions on Circuits and Systems for Video Technology.","DOI":"10.1109\/TCSVT.2022.3192542"},{"key":"3267_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., & Torralba, A. (2018). Temporal relational reasoning in videos. In Proceedings of the European conference on computer vision (pp. 803\u2013 818).","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"3267_CR28","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., & Han, S. (2019). Tsm: Temporal shift module for efficient video understanding. In 2019 IEEE\/CVF international conference on computer vision (pp. 7082\u2013 7092).","DOI":"10.1109\/ICCV.2019.00718"},{"issue":"1","key":"3267_CR29","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1109\/TCSVT.2020.2969464","volume":"31","author":"F Peng","year":"2020","unstructured":"Peng, F., Lin, Z.-X., Zhang, X., & Long, M. (2020). A semi-fragile reversible watermarking for authenticating 2d engineering graphics based on improved region nesting. IEEE Transactions on Circuits and Systems for Video Technology, 31(1), 411\u2013424.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"9","key":"3267_CR30","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/TIFS.2018.2819122","volume":"13","author":"Z-X Lin","year":"2018","unstructured":"Lin, Z.-X., Peng, F., & Long, M. (2018). A low-distortion reversible watermarking for 2d engineering graphics based on region nesting. IEEE Transactions on Information Forensics and Security, 13(9), 2372\u20132382.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"3267_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van Gool, L. (2016). Temporal segment networks: Towards good practices for deep action recognition. In European conference on computer vision (pp. 20\u2013 36). Springer.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"3267_CR32","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 2019 IEEE\/CVF International conference on computer vision (pp 2000\u2013 2009).","DOI":"10.1109\/ICCV.2019.00209"},{"key":"3267_CR33","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 2020 IEEE\/CVF conference on computer vision and pattern recognition (pp. 906\u2013 915).","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"3267_CR34","doi-asserted-by":"publisher","first-page":"11669","DOI":"10.1609\/aaai.v34i07.6836","volume":"34","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., Li, J., Huang, F., & Lu, T. (2020). Teinet: Towards an efficient architecture for video recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 11669\u201311676.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"3267_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., & Smolic, A. (2021). Action-net: Multipath excitation for action recognition. In 2021 IEEE\/CVF conference on computer vision and pattern recognition (pp. 13209\u2013 13218).","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"3267_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., & Wu, G. (2021). Tdn: Temporal difference networks for efficient action recognition. In 2021 IEEE\/CVF conference on computer vision and pattern recognition (pp. 1895\u2013 1904).","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"3267_CR37","doi-asserted-by":"crossref","unstructured":"Rao, Y., & Ni, J. (2021). Self-supervised domain adaptation for forgery localization of jpeg compressed images. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 15034\u2013 15043).","DOI":"10.1109\/ICCV48922.2021.01476"},{"key":"3267_CR38","doi-asserted-by":"crossref","unstructured":"Qin, X., Li, B., Tan, S., Tang, W., & Huang, J. (2022). Gradually enhanced adversarial perturbations on color pixel vectors for image steganography. IEEE Transactions on Circuits and Systems for Video Technology.","DOI":"10.1109\/TCSVT.2022.3148406"},{"key":"3267_CR39","doi-asserted-by":"crossref","unstructured":"Qin, X., Tan, S., Tang, W., Li, B., & Huang, J. (2021). Image steganography based on iterative adversarial perturbations onto a synchronized-directions sub-image. In ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2705\u2013 2709). IEEE","DOI":"10.1109\/ICASSP39728.2021.9414055"},{"issue":"1\u20133","key":"3267_CR40","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BK Horn","year":"1981","unstructured":"Horn, B. K., & Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17(1\u20133), 185\u2013203.","journal-title":"Artificial Intelligence"},{"key":"3267_CR41","doi-asserted-by":"publisher","unstructured":"Fernando, B., Gavves, E., Oramas, J., & Ghodrati, A., & Tuytelaars, T. (2017). Rank pooling for action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 773\u2013787. https:\/\/doi.org\/10.1109\/TPAMI.2016.2558148","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"3267_CR42","doi-asserted-by":"publisher","first-page":"4667","DOI":"10.1109\/TIP.2021.3073867","volume":"30","author":"Y Hu","year":"2021","unstructured":"Hu, Y., Liu, M., Su, X., Gao, Z., & Nie, L. (2021). Video moment localization via deep cross-modal hashing. IEEE Transactions on Image Processing, 30, 4667\u20134677. https:\/\/doi.org\/10.1109\/TIP.2021.3073867","journal-title":"IEEE Transactions on Image Processing"},{"key":"3267_CR43","doi-asserted-by":"publisher","unstructured":"Gan, C., Wang, N., Yang, Y., Yeung, D.-Y., Hauptmann, A.G. (2015). Devnet: A deep event network for multimedia event detection and evidence recounting. In 2015 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2568\u2013 2577). https:\/\/doi.org\/10.1109\/CVPR.2015.7298872","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"3267_CR44","doi-asserted-by":"publisher","first-page":"13926","DOI":"10.1109\/ACCESS.2022.3144035","volume":"10","author":"J Jiang","year":"2022","unstructured":"Jiang, J., & Zhang, Y. (2022). An improved action recognition network with temporal extraction and feature enhancement. IEEE Access, 10, 13926\u201313935. https:\/\/doi.org\/10.1109\/ACCESS.2022.3144035","journal-title":"IEEE Access"},{"issue":"5","key":"3267_CR45","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/TCSVT.2021.3103677","volume":"32","author":"Z Shen","year":"2022","unstructured":"Shen, Z., Wu, X.-J., & Xu, T. (2022). Fexnet: Foreground extraction network for human action recognition. IEEE Transactions on Circuits and Systems for Video Technology, 32(5), 3141\u20133151. https:\/\/doi.org\/10.1109\/TCSVT.2021.3103677","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"4","key":"3267_CR46","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TPAMI.2020.3029554","volume":"44","author":"X Long","year":"2022","unstructured":"Long, X., de Melo, G., He, D., Li, F., Chi, Z., Wen, S., & Gan, C. (2022). Purely attention based local feature integration for video classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4), 2140\u20132154. https:\/\/doi.org\/10.1109\/TPAMI.2020.3029554","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"3267_CR47","doi-asserted-by":"publisher","unstructured":"Wang, X., Farhadi, A., & Gupta, A. (2016) Actions transformations. In 2016 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2658\u2013 2667). https:\/\/doi.org\/10.1109\/CVPR.2016.291","DOI":"10.1109\/CVPR.2016.291"},{"key":"3267_CR48","doi-asserted-by":"publisher","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., & Huang, J. (2018). End-to-end learning of motion representation for video understanding. In 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 6016\u2013 6025). https:\/\/doi.org\/10.1109\/CVPR.2018.00630","DOI":"10.1109\/CVPR.2018.00630"},{"issue":"12","key":"3267_CR49","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TPAMI.2017.2769085","volume":"40","author":"H Bilen","year":"2018","unstructured":"Bilen, H., Fernando, B., Gavves, E., & Vedaldi, A. (2018). Action recognition with dynamic image networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2799\u20132813. https:\/\/doi.org\/10.1109\/TPAMI.2017.2769085","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"3267_CR50","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s11263-019-01248-3","volume":"128","author":"SA Khowaja","year":"2020","unstructured":"Khowaja, S. A., & Lee, S.-L. (2020). Semantic image networks for human action recognition. International Journal of Computer Vision, 128(2), 393\u2013419.","journal-title":"International Journal of Computer Vision"},{"key":"3267_CR51","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TIP.2020.3038372","volume":"30","author":"Z Gao","year":"2021","unstructured":"Gao, Z., Guo, L., Guan, W., Liu, A.-A., Ren, T., & Chen, S. (2021). A pairwise attentive adversarial spatiotemporal network for cross-domain few-shot action recognition-r2. IEEE Transactions on Image Processing, 30, 767\u2013782. https:\/\/doi.org\/10.1109\/TIP.2020.3038372","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"3267_CR52","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TNNLS.2020.3041018","volume":"33","author":"Z Gao","year":"2022","unstructured":"Gao, Z., Guo, L., Ren, T., Liu, A.-A., Cheng, Z.-Y., & Chen, S. (2022). Pairwise two-stream convnets for cross-domain action recognition with small data. IEEE Transactions on Neural Networks and Learning Systems, 33(3), 1147\u20131161. https:\/\/doi.org\/10.1109\/TNNLS.2020.3041018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"3267_CR53","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 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 6450\u2013 6459).","DOI":"10.1109\/CVPR.2018.00675"},{"key":"3267_CR54","doi-asserted-by":"publisher","unstructured":"Tran, D., Wang, H., Feiszli, M., & Torresani, L. (2019). Video classification with channel-separated convolutional networks. In 2019 IEEE\/CVF international conference on computer vision (ICCV) (pp. 5551\u2013 5560). https:\/\/doi.org\/10.1109\/ICCV.2019.00565","DOI":"10.1109\/ICCV.2019.00565"},{"key":"3267_CR55","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Singh, K., & Brox, T. (2018). Eco: Efficient convolutional network for online video understanding. In Proceedings of the European conference on computer vision (pp. 695\u2013 712).","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"3267_CR56","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K. ( 2019). Slowfast networks for video recognition. In 2019 IEEE\/CVF international conference on computer vision (pp. 6201\u2013 6210).","DOI":"10.1109\/ICCV.2019.00630"},{"key":"3267_CR57","doi-asserted-by":"publisher","first-page":"5626","DOI":"10.1109\/TIP.2021.3087348","volume":"30","author":"Z Yu","year":"2021","unstructured":"Yu, Z., Zhou, B., Wan, J., Wang, P., Chen, H., Liu, X., Li, S. Z., & Zhao, G. (2021). Searching multi-rate and multi-modal temporal enhanced networks for gesture recognition. IEEE Transactions on Image Processing, 30, 5626\u20135640. https:\/\/doi.org\/10.1109\/TIP.2021.3087348","journal-title":"IEEE Transactions on Image Processing"},{"key":"3267_CR58","doi-asserted-by":"publisher","first-page":"4583","DOI":"10.1109\/TIP.2020.2974061","volume":"29","author":"X Liu","year":"2020","unstructured":"Liu, X., Shi, H., Hong, X., Chen, H., Tao, D., & Zhao, G. (2020). 3d skeletal gesture recognition via hidden states exploration. IEEE Transactions on Image Processing, 29, 4583\u20134597. https:\/\/doi.org\/10.1109\/TIP.2020.2974061","journal-title":"IEEE Transactions on Image Processing"},{"key":"3267_CR59","doi-asserted-by":"publisher","first-page":"1841","DOI":"10.1109\/TMM.2020.3003783","volume":"23","author":"X Liu","year":"2021","unstructured":"Liu, X., & Zhao, G. (2021). 3d skeletal gesture recognition via discriminative coding on time-warping invariant riemannian trajectories. IEEE Transactions on Multimedia, 23, 1841\u20131854. https:\/\/doi.org\/10.1109\/TMM.2020.3003783","journal-title":"IEEE Transactions on Multimedia"},{"issue":"6","key":"3267_CR60","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 Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1510\u20131517.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"3267_CR61","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. ICLR"},{"key":"3267_CR62","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., Hoppe, F., Thurau, C., Bax, I., & Memisevic, R. (2017). The something something video database for learning and evaluating visual common sense. In 2017 IEEE international conference on computer vision (pp. 5843\u2013 5851).","DOI":"10.1109\/ICCV.2017.622"},{"key":"3267_CR63","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In 2018 IEEE\/CVF conference on computer vision and pattern recognition (pp. 7794\u2013 7803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3267_CR64","doi-asserted-by":"crossref","unstructured":"Wang, X., & Gupta, A. (2018). Videos as space-time region graphs. In Proceedings of the European conference on computer vision (pp. 399\u2013 417)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"3267_CR65","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248\u2013 255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3267_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In 2016 IEEE conference on computer vision and pattern recognition (pp. 2921\u2013 2929).","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Wireless Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11276-023-03267-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11276-023-03267-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11276-023-03267-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T16:29:51Z","timestamp":1722616191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11276-023-03267-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":66,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3267"],"URL":"https:\/\/doi.org\/10.1007\/s11276-023-03267-y","relation":{},"ISSN":["1022-0038","1572-8196"],"issn-type":[{"value":"1022-0038","type":"print"},{"value":"1572-8196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]},"assertion":[{"value":"30 January 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}