{"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/motion-fused-frames-data-level-fusion","title":"Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition","arxiv_id":"1804.07187","date":"2018-04-19","proceeding":null,"authors":["Okan Köpüklü","Neslihan Köse","Gerhard Rigoll"],"abstract":"Acquiring spatio-temporal states of an action is the most crucial step for\naction classification. In this paper, we propose a data level fusion strategy,\nMotion Fused Frames (MFFs), designed to fuse motion information into static\nimages as better representatives of spatio-temporal states of an action. MFFs\ncan be used as input to any deep learning architecture with very little\nmodification on the network. We evaluate MFFs on hand gesture recognition tasks\nusing three video datasets - Jester, ChaLearn LAP IsoGD and NVIDIA Dynamic Hand\nGesture Datasets - which require capturing long-term temporal relations of hand\nmovements. Our approach obtains very competitive performance on Jester and\nChaLearn benchmarks with the classification accuracies of 96.28% and 57.4%,\nrespectively, while achieving state-of-the-art performance with 84.7% accuracy\non NVIDIA benchmark.","url_abs":"http://arxiv.org/abs/1804.07187v2","url_pdf":"http://arxiv.org/pdf/1804.07187v2.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":"motion-fused-frames-data-level-fusion","repo_url":"https://github.com/okankop/MFF-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"hand-gesture-recognition","task_name":"Hand Gesture Recognition"},{"task_slug":"hand-gesture-recognition-1","task_name":"Hand-Gesture Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-gesture-recognition-on-chalean-test","task":"Hand Gesture Recognition","dataset":"ChaLean test","model":"8-MFFs-3f1c","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"56.7"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-chalearn-val","task":"Hand Gesture Recognition","dataset":"ChaLearn val","model":"8-MFFs-3f1c (5 crop)","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-jester-test","task":"Hand Gesture Recognition","dataset":"Jester test","model":"DRX3D","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-jester-val","task":"Hand Gesture Recognition","dataset":"Jester val","model":"8-MFFs-3f1c (5 crop)","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"96.33","Top 5 Accuracy":"99.86"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-nvgesture-1","task":"Hand Gesture Recognition","dataset":"NVGesture","model":"8-MFFs-3f1c","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"84.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07187","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}