{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stnet-local-and-global-spatial-temporal","title":"StNet: Local and Global Spatial-Temporal Modeling for Action Recognition","arxiv_id":"1811.01549","date":"2018-11-05","proceeding":null,"authors":["Dongliang He","Zhichao Zhou","Chuang Gan","Fu Li","Xiao Liu","Yandong Li","Li-Min Wang","Shilei Wen"],"abstract":"Despite the success of deep learning for static image understanding, it\nremains unclear what are the most effective network architectures for the\nspatial-temporal modeling in videos. In this paper, in contrast to the existing\nCNN+RNN or pure 3D convolution based approaches, we explore a novel spatial\ntemporal network (StNet) architecture for both local and global\nspatial-temporal modeling in videos. Particularly, StNet stacks N successive\nvideo frames into a \\emph{super-image} which has 3N channels and applies 2D\nconvolution on super-images to capture local spatial-temporal relationship. To\nmodel global spatial-temporal relationship, we apply temporal convolution on\nthe local spatial-temporal feature maps. Specifically, a novel temporal\nXception block is proposed in StNet. It employs a separate channel-wise and\ntemporal-wise convolution over the feature sequence of video. Extensive\nexperiments on the Kinetics dataset demonstrate that our framework outperforms\nseveral state-of-the-art approaches in action recognition and can strike a\nsatisfying trade-off between recognition accuracy and model complexity. We\nfurther demonstrate the generalization performance of the leaned video\nrepresentations on the UCF101 dataset.","url_abs":"http://arxiv.org/abs/1811.01549v3","url_pdf":"http://arxiv.org/pdf/1811.01549v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/BigLazyPig/Pytorch-StNet-Full-Implement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/hyperfraise/Pytorch-StNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/hyperfraise/StNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/stnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/2023-MindSpore-4/Code7/tree/main/stnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/stnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/kingcong/stnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"stnet-local-and-global-spatial-temporal","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/stnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.01549","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}