{"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/graph-distillation-for-action-detection-with","title":"Graph Distillation for Action Detection with Privileged Modalities","arxiv_id":"1712.00108","date":"2017-11-30","proceeding":"ECCV 2018 9","authors":["Zelun Luo","Jun-Ting Hsieh","Lu Jiang","Juan Carlos Niebles","Li Fei-Fei"],"abstract":"We propose a technique that tackles action detection in multimodal videos\nunder a realistic and challenging condition in which only limited training data\nand partially observed modalities are available. Common methods in transfer\nlearning do not take advantage of the extra modalities potentially available in\nthe source domain. On the other hand, previous work on multimodal learning only\nfocuses on a single domain or task and does not handle the modality discrepancy\nbetween training and testing. In this work, we propose a method termed graph\ndistillation that incorporates rich privileged information from a large-scale\nmultimodal dataset in the source domain, and improves the learning in the\ntarget domain where training data and modalities are scarce. We evaluate our\napproach on action classification and detection tasks in multimodal videos, and\nshow that our model outperforms the state-of-the-art by a large margin on the\nNTU RGB+D and PKU-MMD benchmarks. The code is released at\nhttp://alan.vision/eccv18_graph/.","url_abs":"http://arxiv.org/abs/1712.00108v2","url_pdf":"http://arxiv.org/pdf/1712.00108v2.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":"graph-distillation-for-action-detection-with","repo_url":"https://github.com/google/graph_distillation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.00108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}