{"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/r-stan-residual-spatial-temporal-attention","title":"R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition","arxiv_id":null,"date":"2019-06-19","proceeding":"IEEE Access ( Volume: 7 ) 2019 6","authors":["Quanle Liu","Xiangjiu Che","Mei Bie"],"abstract":"Two-stream network architecture has the ability to capture temporal and spatial features from videos simultaneously and has achieved excellent performance on video action recognition tasks. However, there is a fair amount of redundant information in both temporal and spatial dimensions in videos, which increases the complexity of network learning. To solve this problem, we propose residual spatial-temporal attention network (R-STAN), a feed-forward convolutional neural network using residual learning and spatial-temporal attention mechanism for video action recognition, which makes the network focus more on discriminative temporal and spatial features. In our R-STAN, each stream is constructed by stacking residual spatial-temporal attention blocks (R-STAB), the spatial-temporal attention modules integrated in the residual blocks have the ability to generate attention-aware features along temporal and spatial dimensions, which largely reduce the redundant information. Together with the specific characteristic of residual learning, we are able to construct a very deep network for learning spatial-temporal information in videos. With the layers going deeper, the attention-aware features from the different R-STABs can change adaptively. We validate our R-STAN through a large number of experiments on UCF101 and HMDB51 datasets. Our experiments show that our proposed network combined with residual learning and spatial-temporal attention mechanism contributes substantially to the performance of video action recognition.","url_abs":"https://doi.org/10.1109/ACCESS.2019.2923651","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8740848","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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"R-STAN-50","rank_in_archive_order":65,"of":77,"metrics":{"Average accuracy of 3 splits":"62.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"R-STAN-152","rank_in_archive_order":70,"of":77,"metrics":{"Average accuracy of 3 splits":"55.16"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"R-STAN-101","rank_in_archive_order":53,"of":91,"metrics":{"3-fold Accuracy":"94.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"R-STAN-50","rank_in_archive_order":67,"of":91,"metrics":{"3-fold Accuracy":"91.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}