{"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/making-the-invisible-visible-action","title":"Making the Invisible Visible: Action Recognition Through Walls and Occlusions","arxiv_id":"1909.09300","date":"2019-09-20","proceeding":"ICCV 2019 10","authors":["Tianhong Li","Lijie Fan","Ming-Min Zhao","Yingcheng Liu","Dina Katabi"],"abstract":"Understanding people's actions and interactions typically depends on seeing them. Automating the process of action recognition from visual data has been the topic of much research in the computer vision community. But what if it is too dark, or if the person is occluded or behind a wall? In this paper, we introduce a neural network model that can detect human actions through walls and occlusions, and in poor lighting conditions. Our model takes radio frequency (RF) signals as input, generates 3D human skeletons as an intermediate representation, and recognizes actions and interactions of multiple people over time. By translating the input to an intermediate skeleton-based representation, our model can learn from both vision-based and RF-based datasets, and allow the two tasks to help each other. We show that our model achieves comparable accuracy to vision-based action recognition systems in visible scenarios, yet continues to work accurately when people are not visible, hence addressing scenarios that are beyond the limit of today's vision-based action recognition.","url_abs":"https://arxiv.org/abs/1909.09300v1","url_pdf":"https://arxiv.org/pdf/1909.09300v1.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":[],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"rf-based-pose-estimation","task_name":"RF-based Pose Estimation"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rf-based-pose-estimation-on-rf-mmd-1","task":"RF-based Pose Estimation","dataset":"RF-MMD","model":"RF-Action","rank_in_archive_order":1,"of":1,"metrics":{"mAP (@0.1, Through-wall)":"86.5","mAP (@0.1, Visible)":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"RF-Action","rank_in_archive_order":80,"of":135,"metrics":{"Accuracy (CS)":"86.8","Accuracy (CV)":"91.6"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-pku-mmd","task":"Skeleton Based Action Recognition","dataset":"PKU-MMD","model":"RF-Action","rank_in_archive_order":1,"of":4,"metrics":{"mAP@0.50 (CS)":"92.9","mAP@0.50 (CV)":"94.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.09300","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}