{"id":"https://openalex.org/W4408353438","doi":"https://doi.org/10.1109/icassp49660.2025.10890444","title":"DACAT: Dual-stream Adaptive Clip-aware Time Modeling for Robust Online Surgical Phase Recognition","display_name":"DACAT: Dual-stream Adaptive Clip-aware Time Modeling for Robust Online Surgical Phase Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353438","doi":"https://doi.org/10.1109/icassp49660.2025.10890444"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5050942308","display_name":"Kaixiang Yang","orcid":"https://orcid.org/0000-0003-2180-2101"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixiang Yang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430031","display_name":"Qiang Li","orcid":"https://orcid.org/0000-0002-9815-4432"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Li","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449952","display_name":"Zhiwei Wang","orcid":"https://orcid.org/0000-0002-1612-8573"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Wang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5326,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87367011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/computer-science","display_name":"Computer science","score":0.7769283056259155},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6107679605484009},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.42926186323165894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32213687896728516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769283056259155},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6107679605484009},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.42926186323165894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32213687896728516},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338440","display_name":"HORIZON EUROPE Health","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2266464013","https://openalex.org/W2550143307","https://openalex.org/W2777273430","https://openalex.org/W2901879337","https://openalex.org/W2979536508","https://openalex.org/W2979797179","https://openalex.org/W2990205821","https://openalex.org/W3090913119","https://openalex.org/W3092562667","https://openalex.org/W3094502228","https://openalex.org/W3150630416","https://openalex.org/W3201659970","https://openalex.org/W3203204495","https://openalex.org/W4296054452","https://openalex.org/W4312443924","https://openalex.org/W4320713037","https://openalex.org/W4364321974","https://openalex.org/W4385245566","https://openalex.org/W4386076493","https://openalex.org/W4390873624","https://openalex.org/W4390874575","https://openalex.org/W4390970721","https://openalex.org/W4392352518","https://openalex.org/W4408352881","https://openalex.org/W6638667902","https://openalex.org/W6870839691","https://openalex.org/W6876291677"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Surgical":[0],"phase":[1,25,173],"recognition":[2],"has":[3],"become":[4],"a":[5,54,64,84,98,112],"crucial":[6],"requirement":[7],"in":[8,48,200],"laparoscopic":[9],"surgery,":[10],"enabling":[11],"various":[12],"clinical":[13],"applications":[14],"like":[15],"surgical":[16,24,56,172],"risk":[17],"forecasting.":[18],"Current":[19],"methods":[20],"typically":[21],"identify":[22],"the":[23,31,76,93,104,108,122,127,134,140,153,166,188],"using":[26,126],"individual":[27],"frame-wise":[28,90,105,129],"embeddings":[29],"as":[30],"fundamental":[32],"unit":[33],"for":[34,169],"time":[35,167],"modeling.":[36],"However,":[37],"this":[38,59],"approach":[39],"is":[40,118,147],"overly":[41],"sensitive":[42],"to":[43,74,102,120,131,164],"current":[44,109,128,154],"observations,":[45],"often":[46],"resulting":[47],"discontinuous":[49],"and":[50,156,161,185,208,213],"erroneous":[51],"predictions":[52],"within":[53],"complete":[55],"phase.":[57],"In":[58,79,92],"paper,":[60],"we":[61],"propose":[62],"DACAT,":[63],"novel":[65],"dual-stream":[66],"model":[67],"that":[68],"adaptively":[69,132],"learns":[70],"clip-aware":[71,144],"context":[72,145],"information":[73],"enhance":[75,165],"temporal":[77],"relationship.":[78],"one":[80],"stream,":[81,95],"DACAT":[82,96,193],"pretrains":[83],"frame":[85,100,155],"encoder,":[86],"caching":[87],"all":[88],"historical":[89],"features.":[91],"other":[94],"fine-tunes":[97],"new":[99],"encoder":[101],"extract":[103],"feature":[106,130,141,146],"at":[107,204,218],"moment.":[110],"Additionally,":[111],"max":[113],"clip-response":[114],"read-out":[115],"(Max-R)":[116],"module":[117],"introduced":[119],"bridge":[121],"two":[123],"streams":[124],"by":[125],"fetch":[133],"most":[135],"relevant":[136],"past":[137],"clip":[138],"from":[139],"cache.":[142],"The":[143,175],"then":[148],"encoded":[149],"via":[150],"cross-attention":[151],"between":[152],"its":[157],"fetched":[158],"adaptive":[159],"clip,":[160],"further":[162],"utilized":[163],"modeling":[168],"accurate":[170],"online":[171],"recognition.":[174],"benchmark":[176],"results":[177],"on":[178],"three":[179],"public":[180],"datasets,":[181],"i.e.,":[182],"Cholec80,":[183],"M2CAI16,":[184],"AutoLaparo,":[186],"demonstrate":[187],"superiority":[189],"of":[190,203],"our":[191],"proposed":[192],"over":[194],"existing":[195],"state-of-the-art":[196],"methods,":[197],"with":[198],"improvements":[199],"Jaccard":[201],"scores":[202],"least":[205],"4.5%,":[206],"4.6%,":[207],"2.7%,":[209],"respectively.":[210],"Our":[211],"code":[212],"models":[214],"have":[215],"been":[216],"released":[217],"https://github.com/kk42yy/DACAT.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}