{"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/beyond-temporal-pooling-recurrence-and","title":"Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video","arxiv_id":"1506.01911","date":"2015-06-05","proceeding":null,"authors":["Lionel Pigou","Aäron van den Oord","Sander Dieleman","Mieke Van Herreweghe","Joni Dambre"],"abstract":"Recent studies have demonstrated the power of recurrent neural networks for\nmachine translation, image captioning and speech recognition. For the task of\ncapturing temporal structure in video, however, there still remain numerous\nopen research questions. Current research suggests using a simple temporal\nfeature pooling strategy to take into account the temporal aspect of video. We\ndemonstrate that this method is not sufficient for gesture recognition, where\ntemporal information is more discriminative compared to general video\nclassification tasks. We explore deep architectures for gesture recognition in\nvideo and propose a new end-to-end trainable neural network architecture\nincorporating temporal convolutions and bidirectional recurrence. Our main\ncontributions are twofold; first, we show that recurrence is crucial for this\ntask; second, we show that adding temporal convolutions leads to significant\nimprovements. We evaluate the different approaches on the Montalbano gesture\nrecognition dataset, where we achieve state-of-the-art results.","url_abs":"http://arxiv.org/abs/1506.01911v3","url_pdf":"http://arxiv.org/pdf/1506.01911v3.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":"beyond-temporal-pooling-recurrence-and","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":"image-captioning","task_name":"Image Captioning"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gesture-recognition-on-montalbano","task":"Gesture Recognition","dataset":"Montalbano","model":"Temp Conv + LSTM","rank_in_archive_order":1,"of":1,"metrics":{"Error rate":"2.77","Jaccard (Mean)":"90.6","Precision":"94.49","Recall":"94.57"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.01911","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}