{"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/activity-driven-weakly-supervised-object","title":"Activity Driven Weakly Supervised Object Detection","arxiv_id":"1904.01665","date":"2019-04-02","proceeding":"CVPR 2019 6","authors":["Zhenheng Yang","Dhruv Mahajan","Deepti Ghadiyaram","Ram Nevatia","Vignesh Ramanathan"],"abstract":"Weakly supervised object detection aims at reducing the amount of supervision\nrequired to train detection models. Such models are traditionally learned from\nimages/videos labelled only with the object class and not the object bounding\nbox. In our work, we try to leverage not only the object class labels but also\nthe action labels associated with the data. We show that the action depicted in\nthe image/video can provide strong cues about the location of the associated\nobject. We learn a spatial prior for the object dependent on the action (e.g.\n\"ball\" is closer to \"leg of the person\" in \"kicking ball\"), and incorporate\nthis prior to simultaneously train a joint object detection and action\nclassification model. We conducted experiments on both video datasets and image\ndatasets to evaluate the performance of our weakly supervised object detection\nmodel. Our approach outperformed the current state-of-the-art (SOTA) method by\nmore than 6% in mAP on the Charades video dataset.","url_abs":"http://arxiv.org/abs/1904.01665v1","url_pdf":"http://arxiv.org/pdf/1904.01665v1.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":"action-classification","task_name":"Action Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-4","task":"Weakly Supervised Object Detection","dataset":"Charades","model":"Spatial Prior","rank_in_archive_order":1,"of":6,"metrics":{"MAP":"10.03"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-hico","task":"Weakly Supervised Object Detection","dataset":"HICO-DET","model":"Spatial Prior","rank_in_archive_order":1,"of":4,"metrics":{"MAP":"5.39"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}