{"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/collaborative-spatiotemporal-feature-learning","title":"Collaborative Spatiotemporal Feature Learning for Video Action Recognition","arxiv_id":null,"date":"2019-06-01","proceeding":"CVPR 2019 6","authors":["Chao Li"," Qiaoyong Zhong"," Di Xie"," Shiliang Pu"],"abstract":"Spatiotemporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D). In this paper, we propose a novel neural operation which encodes spatiotemporal features collaboratively by imposing a weight-sharing constraint on the learnable parameters. In particular, we perform 2D convolution along three orthogonal views of volumetric video data, which learns spatial appearance and temporal motion cues respectively. By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other. The complementary features are subsequently fused by a weighted summation whose coefficients are learned end-to-end. Our approach achieves state-of-the-art performance on large-scale benchmarks and won the 1st place in the Moments in Time Challenge 2018. Moreover, based on the learned coefficients of different views, we are able to quantify the contributions of spatial and temporal features. This analysis sheds light on interpretability of the model and may also guide the future design of algorithm for video recognition.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.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":"collaborative-spatiotemporal-feature-learning","repo_url":"https://github.com/hikvision-research/cost","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CoST ResNet-101  (ImageNet pretrain)","rank_in_archive_order":138,"of":207,"metrics":{"Acc@1":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-moments-in-time","task":"Action Classification","dataset":"MiT","model":"CoST (ResNet-101, 32 frames)","rank_in_archive_order":18,"of":29,"metrics":{"Top 1 Accuracy":"32.4%","Top 5 Accuracy":"60.0%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}