{"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/end-to-end-video-level-representation","title":"End-to-end Video-level Representation Learning for Action Recognition","arxiv_id":"1711.04161","date":"2017-11-11","proceeding":null,"authors":["Jiagang Zhu","Wei Zou","Zheng Zhu"],"abstract":"From the frame/clip-level feature learning to the video-level representation\nbuilding, deep learning methods in action recognition have developed rapidly in\nrecent years. However, current methods suffer from the confusion caused by\npartial observation training, or without end-to-end learning, or restricted to\nsingle temporal scale modeling and so on. In this paper, we build upon\ntwo-stream ConvNets and propose Deep networks with Temporal Pyramid Pooling\n(DTPP), an end-to-end video-level representation learning approach, to address\nthese problems. Specifically, at first, RGB images and optical flow stacks are\nsparsely sampled across the whole video. Then a temporal pyramid pooling layer\nis used to aggregate the frame-level features which consist of spatial and\ntemporal cues. Lastly, the trained model has compact video-level representation\nwith multiple temporal scales, which is both global and sequence-aware.\nExperimental results show that DTPP achieves the state-of-the-art performance\non two challenging video action datasets: UCF101 and HMDB51, either by ImageNet\npre-training or Kinetics pre-training.","url_abs":"http://arxiv.org/abs/1711.04161v7","url_pdf":"http://arxiv.org/pdf/1711.04161v7.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":"end-to-end-video-level-representation","repo_url":"https://github.com/zhujiagang/DTPP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}