{"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/recognizing-surgical-activities-with","title":"Recognizing Surgical Activities with Recurrent Neural Networks","arxiv_id":"1606.06329","date":"2016-06-20","proceeding":null,"authors":["Robert DiPietro","Colin Lea","Anand Malpani","Narges Ahmidi","S. Swaroop Vedula","Gyusung I. Lee","Mija R. Lee","Gregory D. Hager"],"abstract":"We apply recurrent neural networks to the task of recognizing surgical\nactivities from robot kinematics. Prior work in this area focuses on\nrecognizing short, low-level activities, or gestures, and has been based on\nvariants of hidden Markov models and conditional random fields. In contrast, we\nwork on recognizing both gestures and longer, higher-level activites, or\nmaneuvers, and we model the mapping from kinematics to gestures/maneuvers with\nrecurrent neural networks. To our knowledge, we are the first to apply\nrecurrent neural networks to this task. Using a single model and a single set\nof hyperparameters, we match state-of-the-art performance for gesture\nrecognition and advance state-of-the-art performance for maneuver recognition,\nin terms of both accuracy and edit distance. Code is available at\nhttps://github.com/rdipietro/miccai-2016-surgical-activity-rec .","url_abs":"http://arxiv.org/abs/1606.06329v2","url_pdf":"http://arxiv.org/pdf/1606.06329v2.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":"recognizing-surgical-activities-with","repo_url":"https://github.com/rdipietro/miccai-2016-surgical-activity-rec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"recognizing-surgical-activities-with","repo_url":"https://github.com/Skori/miccai-2016-surgical-activity-rec-Refactored","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"recognizing-surgical-activities-with","repo_url":"https://github.com/krishnanpooja/Master-Thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/surgical-skills-evaluation-on-jigsaws","task":"Surgical Skills Evaluation","dataset":"JIGSAWS","model":"Bidir. LSTM","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"0.833","Edit Distance":"14.6"},"uses_additional_data":false},{"leaderboard":"/sota/surgical-skills-evaluation-on-mistic-sil","task":"Surgical Skills Evaluation","dataset":"MISTIC-SIL","model":"Bidir. LSTM","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.895","Edit Distance":"19.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}