{"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/learning-deep-and-compact-models-for-gesture","title":"Learning Deep and Compact Models for Gesture Recognition","arxiv_id":"1712.10136","date":"2017-12-29","proceeding":null,"authors":["Koustav Mullick","Anoop M. Namboodiri"],"abstract":"We look at the problem of developing a compact and accurate model for gesture\nrecognition from videos in a deep-learning framework. Towards this we propose a\njoint 3DCNN-LSTM model that is end-to-end trainable and is shown to be better\nsuited to capture the dynamic information in actions. The solution achieves\nclose to state-of-the-art accuracy on the ChaLearn dataset, with only half the\nmodel size. We also explore ways to derive a much more compact representation\nin a knowledge distillation framework followed by model compression. The final\nmodel is less than $1~MB$ in size, which is less than one hundredth of our\ninitial model, with a drop of $7\\%$ in accuracy, and is suitable for real-time\ngesture recognition on mobile devices.","url_abs":"http://arxiv.org/abs/1712.10136v1","url_pdf":"http://arxiv.org/pdf/1712.10136v1.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":"learning-deep-and-compact-models-for-gesture","repo_url":"https://github.com/chriswegmann/drone_steering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gesture-recognition-on-chalearn-2014","task":"Gesture Recognition","dataset":"Chalearn 2014","model":"3D-CNN + LSTM","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"93.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}