{"id":"https://openalex.org/W7161114992","doi":"https://doi.org/10.1145/3746467.3801528","title":"Unified Generative Multimodal Modeling of Surgical Gestures and Phases via Transfer Learning","display_name":"Unified Generative Multimodal Modeling of Surgical Gestures and Phases via Transfer Learning","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7161114992","doi":"https://doi.org/10.1145/3746467.3801528"},"language":null,"primary_location":{"id":"doi:10.1145/3746467.3801528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801528","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746467.3801528","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136142641","display_name":"Hemanth Reddy Madduri","orcid":"https://orcid.org/0009-0009-1209-8344"},"institutions":[{"id":"https://openalex.org/I207123951","display_name":"New Mexico Institute of Mining and Technology","ror":"https://ror.org/005p9kw61","country_code":"US","type":"education","lineage":["https://openalex.org/I207123951"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hemanth Reddy Madduri","raw_affiliation_strings":["Computer Science, New Mexico Institute of Mining and Technology, Socorro, NM, USA"],"raw_orcid":"https://orcid.org/0009-0009-1209-8344","affiliations":[{"raw_affiliation_string":"Computer Science, New Mexico Institute of Mining and Technology, Socorro, NM, USA","institution_ids":["https://openalex.org/I207123951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Texas Tech University, Lubbock, TX, USA"],"raw_orcid":"https://orcid.org/0009-0009-8935-0720","affiliations":[{"raw_affiliation_string":"Texas Tech University, Lubbock, TX, USA","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108063890","display_name":"Jun Zheng","orcid":"https://orcid.org/0000-0001-6727-5867"},"institutions":[{"id":"https://openalex.org/I207123951","display_name":"New Mexico Institute of Mining and Technology","ror":"https://ror.org/005p9kw61","country_code":"US","type":"education","lineage":["https://openalex.org/I207123951"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Zheng","raw_affiliation_strings":["New Mexico Institute of Mining and Technology, Socorro, NM, USA"],"raw_orcid":"https://orcid.org/0000-0001-6727-5867","affiliations":[{"raw_affiliation_string":"New Mexico Institute of Mining and Technology, Socorro, NM, USA","institution_ids":["https://openalex.org/I207123951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075369864","display_name":"Huixin Zhan","orcid":"https://orcid.org/0000-0001-8926-1941"},"institutions":[{"id":"https://openalex.org/I207123951","display_name":"New Mexico Institute of Mining and Technology","ror":"https://ror.org/005p9kw61","country_code":"US","type":"education","lineage":["https://openalex.org/I207123951"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huixin Zhan","raw_affiliation_strings":["New Mexico Institute of Mining and Technology, Socorro, NM, USA"],"raw_orcid":"https://orcid.org/0000-0001-8926-1941","affiliations":[{"raw_affiliation_string":"New Mexico Institute of Mining and Technology, Socorro, NM, USA","institution_ids":["https://openalex.org/I207123951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5136142641"],"corresponding_institution_ids":["https://openalex.org/I207123951"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94453917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.01119999960064888,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8230999708175659},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5328999757766724},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4528999924659729},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.399399995803833},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3986999988555908},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.38510000705718994},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8230999708175659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705000162124634},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5029000043869019},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3986999988555908},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746467.3801528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801528","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746467.3801528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746467.3801528","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Southeast Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4677110016345978,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1970349679","https://openalex.org/W2165698076","https://openalex.org/W2346062110","https://openalex.org/W2568518337","https://openalex.org/W2951058133","https://openalex.org/W4362458937","https://openalex.org/W4389220475","https://openalex.org/W4406855811"],"related_works":[],"abstract_inverted_index":{"Surgical":[0],"gesture":[1,50,68,84,95,103],"prediction,":[2,4,51,54],"phase":[3,53,98,108,163],"and":[5,24,55,75,78,135,146,189,196,207],"skill":[6,57,112,198],"assessment":[7,58,113],"are":[8],"often":[9],"treated":[10],"as":[11],"independent":[12],"tasks,":[13],"which":[14],"limits":[15],"the":[16,93,102,129,132,178],"ability":[17],"of":[18,193],"models":[19],"to":[20,91,185,203],"capture":[21],"shared":[22],"structure":[23],"interdependencies":[25],"across":[26,142,155,205],"these":[27],"related":[28],"objectives.":[29],"We":[30,127],"propose":[31],"a":[32,39,60,67,107],"unified":[33,187],"generative":[34],"multimodal":[35],"framework":[36,64,130,180],"based":[37],"on":[38,82,131],"Discrete":[40],"Denoising":[41],"Diffusion":[42],"Probabilistic":[43],"Model":[44],"(D3PM)":[45],"that":[46,71,120],"jointly":[47],"performs":[48],"surgical":[49,52,83,194,208],"surgeon":[56],"within":[59],"single":[61],"architecture.":[62],"The":[63],"first":[65],"learns":[66],"prediction":[69,99,104,109,164],"model":[70,96],"integrates":[72],"visual,":[73],"linguistic,":[74],"action":[76],"features":[77],"achieves":[79],"strong":[80,153,201],"performance":[81,154],"recognition.":[85],"Transfer":[86],"learning":[87,160],"is":[88,114,181],"then":[89],"used":[90],"adapt":[92],"trained":[94],"for":[97,162],"by":[100,168],"replacing":[101],"head":[105],"with":[106,158,200],"head.":[110],"Surgeon":[111],"enabled":[115],"through":[116],"multi-component":[117],"regression":[118],"heads":[119],"predict":[121],"Global":[122],"Rating":[123],"Scale":[124],"(GRS)":[125],"scores.":[126],"evaluate":[128],"JHU-ISI":[133],"Gesture":[134],"Skill":[136],"Assessment":[137],"Working":[138],"Set":[139],"(JIGSAWS)":[140],"dataset":[141],"suturing,":[143],"needle":[144],"passing,":[145],"knot":[147],"tying":[148],"tasks.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"all":[156],"objectives,":[157],"transfer":[159],"configurations":[161],"improving":[165],"training":[166],"efficiency":[167],"at":[169],"least":[170],"35":[171],"percent":[172],"while":[173],"maintaining":[174],"competitive":[175],"accuracy.":[176],"Overall,":[177],"proposed":[179],"computationally":[182],"efficient":[183],"due":[184],"its":[186],"design":[188],"supports":[190],"joint":[191],"understanding":[192],"behavior":[195],"automated":[197],"assessment,":[199],"potential":[202],"generalize":[204],"tasks":[206],"settings.":[209]},"counts_by_year":[],"updated_date":"2026-05-15T06:12:33.780692","created_date":"2026-05-15T00:00:00"}