{"id":"https://openalex.org/W4289829769","doi":"https://doi.org/10.1109/spcom55316.2022.9840779","title":"Temporal Surgical Gesture Segmentation and Classification in Multi-gesture Robotic Surgery using Fine-tuned features and Calibrated MS-TCN","display_name":"Temporal Surgical Gesture Segmentation and Classification in Multi-gesture Robotic Surgery using Fine-tuned features and Calibrated MS-TCN","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4289829769","doi":"https://doi.org/10.1109/spcom55316.2022.9840779"},"language":"en","primary_location":{"id":"doi:10.1109/spcom55316.2022.9840779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840779","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082997093","display_name":"Snigdha Agarwal","orcid":"https://orcid.org/0009-0008-7262-5022"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Snigdha Agarwal","raw_affiliation_strings":["International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113342815","display_name":"Chakka Sai Pradeep","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chakka Sai Pradeep","raw_affiliation_strings":["International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014371833","display_name":"Neelam Sinha","orcid":"https://orcid.org/0000-0001-8164-8412"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neelam Sinha","raw_affiliation_strings":["International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Networking, Communication and Signal Processing,Bangalore Bengaluru,India","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"Networking, Communication and Signal Processing, International Institute of Information Technology, Bangalore Bengaluru, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.2774,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59874135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8931362628936768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186386823654175},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7904223203659058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7577415108680725},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7203567028045654},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6868370771408081},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5674874782562256},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4765651524066925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4464016258716583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43127983808517456}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8931362628936768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186386823654175},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7904223203659058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7577415108680725},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7203567028045654},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6868370771408081},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5674874782562256},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4765651524066925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4464016258716583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43127983808517456},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom55316.2022.9840779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840779","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2013293242","https://openalex.org/W2065883524","https://openalex.org/W2076978869","https://openalex.org/W2194775991","https://openalex.org/W2491875666","https://openalex.org/W2510642588","https://openalex.org/W2618009704","https://openalex.org/W2619947201","https://openalex.org/W2962711930","https://openalex.org/W2962836302","https://openalex.org/W2963524571","https://openalex.org/W2963853051","https://openalex.org/W2964066956","https://openalex.org/W2964273387","https://openalex.org/W2990503944","https://openalex.org/W3015793166","https://openalex.org/W3109908659","https://openalex.org/W3207523613","https://openalex.org/W6738279089","https://openalex.org/W6776290648","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"Temporal":[0],"Gesture":[1,29],"Segmentation":[2,30],"is":[3],"an":[4,149,182,188],"active":[5],"research":[6],"problem":[7],"for":[8,28,113],"many":[9],"applications":[10],"such":[11],"as":[12,160],"surgical":[13,33,124],"skill":[14],"assessment,":[15],"surgery":[16],"training,":[17],"robotic":[18],"training.":[19],"In":[20,84,101],"this":[21],"paper,":[22],"we":[23,87,104,126,147],"propose":[24,148,197],"a":[25,42,156,176,198,218],"novel":[26,199],"method":[27,50],"on":[31,51,93,135],"untrimmed":[32,99],"videos":[34,53],"of":[35,54,64,97,179,186,190,206,211],"the":[36,55,98,123,136,204,209],"challenging":[37],"JIGSAWS":[38,137],"dataset":[39,138],"by":[40,154],"using":[41,132,139],"two-step":[43],"methodology.":[44],"We":[45,174,195],"train":[46],"and":[47,73,116,181],"evaluate":[48],"our":[49,167],"39":[52],"Suturing":[56],"task":[57],"which":[58,163],"has":[59],"10":[60],"gestures.":[61],"The":[62],"length":[63,76],"gestures":[65],"ranges":[66],"from":[67,78,122,192],"1":[68,79],"second":[69],"to":[70,81,109,169],"75":[71],"seconds":[72],"full":[74,94],"video":[75],"varies":[77],"minute":[80],"5":[82],"minutes.":[83],"step":[85,102],"one,":[86],"extract":[88,119],"encoded":[89],"frame-wise":[90,177],"spatio-temporal":[91],"features":[92,108,121],"temporal":[95,114],"resolution":[96],"videos.":[100],"two,":[103],"use":[105],"these":[106],"extracted":[107],"identify":[110],"gesture":[111,129],"segments":[112,213,216],"segmentation":[115],"classification.":[117],"To":[118],"high-quality":[120],"videos,":[125],"also":[127,196],"pre-train":[128],"classification":[130],"models":[131],"transfer":[133],"learning":[134],"two":[140],"state-of-the-art":[141],"pretrained":[142],"backbone":[143],"architectures.":[144],"For":[145],"segmentation,":[146],"improved":[150],"calibrated":[151],"MS-TCN":[152],"(CMS-TCN)":[153],"introducing":[155],"smoothed":[157],"focal":[158],"loss":[159,161],"function":[162],"helps":[164],"in":[165,217],"regularizing":[166],"TCN":[168],"avoid":[170],"making":[171],"over-confident":[172],"decisions.":[173],"achieve":[175],"accuracy":[178],"89.8%":[180],"Edit":[183],"Distance":[184],"score":[185],"91.5%,":[187],"improvement":[189],"2.2%":[191],"previous":[193],"works.":[194],"evaluation":[200],"metric":[201],"that":[202],"normalizes":[203],"effect":[205],"correctly":[207],"classifying":[208],"frames":[210],"larger":[212],"versus":[214],"smaller":[215],"single":[219],"score.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}