{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T04:03:44Z","timestamp":1788581024411,"version":"build-2803163510"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2021SFGC0701"],"award-info":[{"award-number":["2021SFGC0701"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2020MF139"],"award-info":[{"award-number":["ZR2020MF139"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1016\/j.neunet.2023.09.031","type":"journal-article","created":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T12:20:23Z","timestamp":1695385223000},"page":"496-507","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":17,"special_numbering":"C","title":["A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition"],"prefix":"10.1016","volume":"168","author":[{"given":"Shuang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongji","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8716-3691","authenticated-orcid":false,"given":"Zhiquan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengfeng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengmeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.neunet.2023.09.031_b1","doi-asserted-by":"crossref","first-page":"2433","DOI":"10.1073\/pnas.92.7.2433","article-title":"Visual motion perception","volume":"92","author":"Albright","year":"1995","journal-title":"National Academy of Sciences of the United States"},{"key":"10.1016\/j.neunet.2023.09.031_b2","doi-asserted-by":"crossref","unstructured":"Ashton, E. A., Molinelli, L., Totterman, S., & Parker, K. J. (2002). Evaluation of Reproducibility for Manual and Semi-automated Feature Extraction in CT and MR Images. In Proceedings of international conference on image processing. Rochester, New York, USA.","DOI":"10.1109\/ICIP.2002.1038930"},{"issue":"2","key":"10.1016\/j.neunet.2023.09.031_b3","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1109\/TBDATA.2022.3187413","article-title":"IEMask R-CNN: Information-enhanced mask R-CNN","volume":"9","author":"Bi","year":"2023","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.neunet.2023.09.031_b4","doi-asserted-by":"crossref","unstructured":"Bi, Q., Yu, S., Ji, W., Bian, C., Gong, L., Liu, H., et al. (2021). Local-Global Dual Perception based Deep Multiple Instance Learning for Retinal Disease Classification. In Proceedings of medical image computing and computer assisted intervention. Strasbourg, France.","DOI":"10.1007\/978-3-030-87237-3_6"},{"key":"10.1016\/j.neunet.2023.09.031_b5","first-page":"1","article-title":"All grains, one scheme (AGOS): Learning multigrain instance representation for aerial scene classification","volume":"60","author":"Bi","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2023.09.031_b6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compstruc.2021.106678","article-title":"Recurrent neural network based multiaxial plasticity model with regularization for physics-informed constraints","volume":"258","author":"Borkowski","year":"2022","journal-title":"Computers and Structures"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b7","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","article-title":"Large displacement optical flow: Descriptor matching in variational motion estimation","volume":"33","author":"Brox","year":"2011","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"10.1016\/j.neunet.2023.09.031_b8","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1007\/s11760-022-02324-x","article-title":"Spatial-temporal injection network: Exploiting auxiliary losses for action recognition with apparent difference and self-attention","volume":"17","author":"Cao","year":"2022","journal-title":"Signal, Image and Video Processing"},{"key":"10.1016\/j.neunet.2023.09.031_b9","series-title":"Global context networks","author":"Cao","year":"2020"},{"issue":"9","key":"10.1016\/j.neunet.2023.09.031_b10","doi-asserted-by":"crossref","first-page":"3938","DOI":"10.1109\/TNNLS.2017.2740318","article-title":"Deep manifold learning combined with convolutional neural networks for action recognition","volume":"29","author":"Chen","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2023.09.031_b11","series-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"issue":"1","key":"10.1016\/j.neunet.2023.09.031_b12","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.1016\/j.neunet.2023.09.031_b13","unstructured":"Dlal, N., & Triggs, B. (2015). Histograms of Oriented Gradients for Human Detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. San Diego, USA."},{"issue":"1","key":"10.1016\/j.neunet.2023.09.031_b14","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.jenvman.2015.07.051","article-title":"Automated negotiation in environmental resource management: Review and assessment","volume":"162","author":"Eshragh","year":"2015","journal-title":"Journal of Environmental Management"},{"issue":"8","key":"10.1016\/j.neunet.2023.09.031_b15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"8","key":"10.1016\/j.neunet.2023.09.031_b16","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-excitation networks","volume":"42","author":"Hu","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"10.1016\/j.neunet.2023.09.031_b17","first-page":"1","article-title":"Human action recognition using spatio-temporal multiplier network and attentive correlated temporal feature","volume":"22","author":"Indhumathi","year":"2022","journal-title":"Image and Graphics"},{"issue":"1","key":"10.1016\/j.neunet.2023.09.031_b18","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":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.09.031_b19","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2012). HMDB: A Large Video Database for Human Motion Recognition. In Proceedings of the 2011 international conference on computer vision. Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"11","key":"10.1016\/j.neunet.2023.09.031_b20","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2023.09.031_b21","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, Y., Sui, X., Chen, C., Tjio, G., Ting, D., et al. (2019). Multi-Instance multiscale CNN for Medical Image Classification. In Proceedings of international conference on medical image computing and computer-assisted intervention. Shenzhen, China.","DOI":"10.1007\/978-3-030-32251-9_58"},{"key":"10.1016\/j.neunet.2023.09.031_b22","doi-asserted-by":"crossref","unstructured":"Li, D., Yu, L., He, J., Sun, B., & Ge, F. (2016). Action Recognition Based on Multiple Key Motion History Images. In Proceedings of the IEEE 13th international conference on acoustics, speech, and signal processing. Chengdu, China.","DOI":"10.1109\/ICSP.2016.7877978"},{"issue":"1","key":"10.1016\/j.neunet.2023.09.031_b23","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1109\/TPAMI.2020.3011063","article-title":"Learning representations for facial actions from unlabeled videos","volume":"44","author":"Li","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.09.031_b24","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1016\/j.ins.2022.05.092","article-title":"Spatial-temporal interaction learning based two-stream network for action recognition","volume":"606","author":"Liu","year":"2022","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2023.09.031_b25","doi-asserted-by":"crossref","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","article-title":"End-to-end temporal action detection with transformer","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.09.031_b26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., & Lu, T. (2022). TAM: Temporal Adaptive Module for Video Recognition. In Proceedings of the IEEE\/CVF international conference on computer vision. Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"10.1016\/j.neunet.2023.09.031_b27","doi-asserted-by":"crossref","first-page":"4104","DOI":"10.1109\/TIP.2022.3180585","article-title":"Motion-driven visual tempo learning for video-based action recognition","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"10.1016\/j.neunet.2023.09.031_b28","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"issue":"5","key":"10.1016\/j.neunet.2023.09.031_b29","doi-asserted-by":"crossref","first-page":"3073","DOI":"10.1109\/TCSVT.2021.3100842","article-title":"Dense semantics-assisted networks for video action recognition","volume":"32","author":"Luo","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2023.09.031_b30","unstructured":"Luo, H., Liu, Z., & Liu, X. (2021). Research on Video Image Preprocessing for Monitoring Abnormal Action of Mechanical Operators. In Proceedings of the 2021 international conference on electronics, circuits and information engineering. Zhengzhou, China."},{"key":"10.1016\/j.neunet.2023.09.031_b31","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1109\/TMM.2021.3058050","article-title":"Human action recognition by discriminative feature pooling and video segment attention model","volume":"24","author":"Moniruzzaman","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b32","doi-asserted-by":"crossref","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","article-title":"Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes","volume":"24","author":"Pan","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"4","key":"10.1016\/j.neunet.2023.09.031_b33","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/LGRS.2020.2983464","article-title":"PEGNet: Progressive edge guidance network for semantic segmentation of remote sensing images","volume":"18","author":"Pan","year":"2021","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2023.09.031_b34","doi-asserted-by":"crossref","first-page":"2783","DOI":"10.1109\/ACCESS.2021.3136781","article-title":"Generation of novelty ground truth image using image classification and semantic segmentation for copy-move forgery detection","volume":"10","author":"Rhee","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2023.09.031_b35","series-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b36","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","article-title":"Least squares support vector machine classifiers","volume":"9","author":"Suykens","year":"1999","journal-title":"Neural Processing Letters"},{"key":"10.1016\/j.neunet.2023.09.031_b37","doi-asserted-by":"crossref","unstructured":"Tai, N., Yang, Y., & Wang, S. (2022). Play to Play: A Net-Hitting Motion Based Video Game to Enhance Real Baseball Batting Skill. In Proceedings of the 2022 IEEE international conference on consumer electronics. Taiwan, China.","DOI":"10.1109\/ICCE-Taiwan55306.2022.9869011"},{"key":"10.1016\/j.neunet.2023.09.031_b38","doi-asserted-by":"crossref","unstructured":"Tian, Q., Song, Q., Wang, H., Hu, Z., & Zhu, S. (2021). Verification Code Recognition Based on Convolutional Neural Network. In Proceedings of the 2021 IEEE 4th advanced information management, communicates, electronic and automation control conference. Chongqing, China.","DOI":"10.1109\/IMCEC51613.2021.9482170"},{"key":"10.1016\/j.neunet.2023.09.031_b39","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2016). Learning Spatiotemporal Features with 3D Convolutional Networks. In Proceedings of the 2015 IEEE international conference on computer vision. Santiago, Chile.","DOI":"10.1109\/ICCV.2015.510"},{"key":"10.1016\/j.neunet.2023.09.031_b40","series-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2023.09.031_b41","series-title":"Non-local neural networks","author":"Wang","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2023.09.031_b42","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","article-title":"Dense trajectories and motion boundary descriptors for action recognition","volume":"103","author":"Wang","year":"2013","journal-title":"International Journal of Computer Vision"},{"issue":"6","key":"10.1016\/j.neunet.2023.09.031_b43","doi-asserted-by":"crossref","first-page":"3603","DOI":"10.1109\/TCSVT.2021.3112214","article-title":"Continuous multi-view human action recognition","volume":"32","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b44","first-page":"3347","article-title":"Learning Spatiotemporal and motion features in a unified 2D network for action recognition","volume":"45","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.09.031_b45","series-title":"CBAM: Convolutional block attention module","author":"Woo","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b46","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":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"10.1016\/j.neunet.2023.09.031_b47","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":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2023.09.031_b48","first-page":"1","article-title":"Action recognition using action sequences optimization and two-stream 3D dilated neural network","volume":"2022","author":"Xiong","year":"2022","journal-title":"Computational Intelligence and Neuroscience"},{"key":"10.1016\/j.neunet.2023.09.031_b49","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 2022 IEEE\/CVF conference on computer vision and pattern recognition. Salt Lake City, USA.","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"10.1016\/j.neunet.2023.09.031_b50","series-title":"Segmentation transformer: Object-contextual representations for semantic segmentation","author":"Yuan","year":"2021"},{"key":"10.1016\/j.neunet.2023.09.031_b51","doi-asserted-by":"crossref","first-page":"2375","DOI":"10.1007\/s11263-021-01465-9","article-title":"OCNet: Object context for semantic segmentation","volume":"129","author":"Yuan","year":"2021","journal-title":"International Journal of Computer Vision"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023005270?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023005270?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:33:22Z","timestamp":1760236402000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608023005270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":51,"alternative-id":["S0893608023005270"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.09.031","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2023,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.09.031","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}