{"id":"https://openalex.org/W4388186341","doi":"https://doi.org/10.1145/3581783.3611898","title":"Chain-of-Look Prompting for Verb-centric Surgical Triplet Recognition in Endoscopic Videos","display_name":"Chain-of-Look Prompting for Verb-centric Surgical Triplet Recognition in Endoscopic Videos","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388186341","doi":"https://doi.org/10.1145/3581783.3611898"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5010864350","display_name":"Nan Xi","orcid":"https://orcid.org/0000-0002-7334-7772"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nan Xi","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055403026","display_name":"Jingjing Meng","orcid":"https://orcid.org/0000-0001-9776-4805"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Meng","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103243473","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo, Biffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Biffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010864350"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.9839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78386331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5007","last_page":"5016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9783999919891357,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9783999919891357,"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/T10916","display_name":"Surgical Simulation and Training","score":0.9735999703407288,"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/T11731","display_name":"Global Health and Surgery","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571582198143005},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.6074478030204773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802164077758789},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5363961458206177},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5247343182563782},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4732559025287628},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43384912610054016},{"id":"https://openalex.org/keywords/chain-code","display_name":"Chain code","score":0.4288044273853302},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4248390793800354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.416777640581131},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19755220413208008},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13912087678909302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571582198143005},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.6074478030204773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802164077758789},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5363961458206177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5247343182563782},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4732559025287628},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43384912610054016},{"id":"https://openalex.org/C93058836","wikidata":"https://www.wikidata.org/wiki/Q1453572","display_name":"Chain code","level":3,"score":0.4288044273853302},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4248390793800354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.416777640581131},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19755220413208008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13912087678909302},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W79427242","https://openalex.org/W168769873","https://openalex.org/W1591252397","https://openalex.org/W2121357020","https://openalex.org/W2130233101","https://openalex.org/W2194775991","https://openalex.org/W2754191212","https://openalex.org/W2963647178","https://openalex.org/W3083376569","https://openalex.org/W3091895136","https://openalex.org/W3198377975","https://openalex.org/W3198379050","https://openalex.org/W4285818716","https://openalex.org/W4290877727","https://openalex.org/W4312310776"],"related_works":["https://openalex.org/W77339100","https://openalex.org/W2023786122","https://openalex.org/W578800075","https://openalex.org/W3192242131","https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W949345935"],"abstract_inverted_index":{"Surgical":[0],"triplet":[1,27,53,177],"recognition":[2,28,54,178],"aims":[3],"to":[4,144,169],"recognize":[5,34],"surgical":[6,20,26,52,114,133,152,162,176],"activities":[7,115,163],"as":[8,55,127],"triplets":[9],"(i.e.,<instrument,":[10],"verb,":[11,37],"target":[12,39],">),":[13],"which":[14,89],"provides":[15],"fine-grained":[16],"information":[17],"essential":[18],"for":[19,25,151],"scene":[21],"understanding.":[22],"Existing":[23],"methods":[24,32,172],"rely":[29],"on":[30,173],"compositional":[31],"that":[33],"the":[35,49,67,82,101,109,119,125,128,139,146,157,170,174],"instrument,":[36],"and":[38,64,105,164],"simultaneously.":[40],"In":[41],"contrast,":[42],"our":[43],"method,":[44],"called":[45],"chain-of-look":[46],"prompting,":[47],"casts":[48],"problem":[50,92],"of":[51,72,96,121,130],"visual":[56,106,148,158],"prompt":[57,149],"generation":[58],"from":[59],"large-scale":[60],"vision-language":[61],"(VL)":[62],"models,":[63],"explicitly":[65],"decomposes":[66],"task":[68],"into":[69,93],"a":[70,91,94],"series":[71],"video":[73],"reasoning":[74,98,159],"processes.":[75],"Chain-of-Look":[76],"prompting":[77,84],"is":[78,183],"inspired":[79],"by:":[80],"(1)":[81],"chain-of-thought":[83],"in":[85,108,132],"natural":[86],"language":[87,142],"processing,":[88],"divides":[90],"sequence":[95],"intermediate":[97],"steps;":[99],"(2)":[100],"inter-dependency":[102],"between":[103],"motion":[104],"appearance":[107],"human":[110],"vision":[111],"system.":[112],"Since":[113],"are":[116],"conveyed":[117],"by":[118],"actions":[120],"physicians,":[122],"we":[123,137],"regard":[124],"verbs":[126],"carrier":[129],"semantics":[131],"endoscopic":[134],"videos.":[135],"Additionally,":[136],"utilize":[138],"BioMed":[140],"large":[141],"model":[143],"calibrate":[145],"generated":[147],"features":[150],"scenarios.":[153],"Our":[154],"approach":[155],"captures":[156],"processes":[160],"underlying":[161],"achieves":[165],"better":[166],"performance":[167],"compared":[168],"state-of-the-art":[171],"largest":[175],"dataset,":[179],"CholecT50.":[180],"The":[181],"code":[182],"available":[184],"at":[185],"https://github.com/southnx/CoLSurgical.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}