{"id":"https://openalex.org/W4415538790","doi":"https://doi.org/10.1145/3746027.3755167","title":"Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation","display_name":"Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538790","doi":"https://doi.org/10.1145/3746027.3755167"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755167","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5019769019","display_name":"Zhaofeng Shi","orcid":"https://orcid.org/0000-0001-6313-8670"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaofeng Shi","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0001-6313-8670","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434602","display_name":"Heqian Qiu","orcid":"https://orcid.org/0000-0002-0963-0311"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heqian Qiu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-0963-0311","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-3745-0262","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075737786","display_name":"Qingbo Wu","orcid":"https://orcid.org/0000-0003-2936-6340"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbo Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-2936-6340","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617043","display_name":"Fanman Meng","orcid":"https://orcid.org/0000-0002-3016-2567"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanman Meng","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-3016-2567","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114378292","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-7481-095X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-7481-095X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019769019"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28782807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3731","last_page":"3740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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":0.9988999962806702,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9984999895095825,"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":0.9969000220298767,"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/closed-captioning","display_name":"Closed captioning","score":0.7027999758720398},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.6571999788284302},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6463000178337097},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5044000148773193},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4918999969959259},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4343000054359436},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39989998936653137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195000052452087},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7027999758720398},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6463000178337097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6166999936103821},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3125},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2702000141143799}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755167","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2652491850","display_name":null,"funder_award_id":"No. U23A20286, No. 62301121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2034014085","https://openalex.org/W2136668269","https://openalex.org/W2610060393","https://openalex.org/W2741156154","https://openalex.org/W2795307598","https://openalex.org/W2804208182","https://openalex.org/W2952132648","https://openalex.org/W2962799512","https://openalex.org/W2963863119","https://openalex.org/W2963916161","https://openalex.org/W3022532439","https://openalex.org/W3043142510","https://openalex.org/W3047922786","https://openalex.org/W3107094551","https://openalex.org/W3123364653","https://openalex.org/W3163585755","https://openalex.org/W3177419066","https://openalex.org/W3202237431","https://openalex.org/W3205786327","https://openalex.org/W3207447090","https://openalex.org/W3217412301","https://openalex.org/W4207072548","https://openalex.org/W4214663214","https://openalex.org/W4281729400","https://openalex.org/W4282981352","https://openalex.org/W4313071313","https://openalex.org/W4386066385","https://openalex.org/W4387741824","https://openalex.org/W4390873954","https://openalex.org/W4402726946","https://openalex.org/W4402727748","https://openalex.org/W4402727916","https://openalex.org/W4403561465","https://openalex.org/W4403780703"],"related_works":[],"abstract_inverted_index":{"Even":[0],"from":[1,43,149],"an":[2],"early":[3],"age,":[4],"humans":[5],"naturally":[6],"adapt":[7],"between":[8,199],"exocentric":[9],"(Exo)":[10],"and":[11,53,94,137,175,196,202,216],"egocentric":[12],"(Ego)":[13],"perspectives":[14],"to":[15,40,48,68,85,144,163,169,188],"understand":[16],"daily":[17],"procedural":[18],"activities.":[19],"Inspired":[20],"by":[21,91,230],"this":[22],"cognitive":[23],"ability,":[24],"we":[25,99,123,182,209],"propose":[26,100,124,210],"a":[27,101,125,133,150,211,231],"novel":[28],"Unsupervised":[29],"Ego-Exo":[30,104,120],"Dense":[31],"Procedural":[32],"Activity":[33],"Captioning":[34],"(UE^2":[35],"DPAC)":[36],"task,":[37],"which":[38,225],"aims":[39],"transfer":[41],"knowledge":[42],"the":[44,50,59,70,81,86,110,114,118,139,154,161,166,171,177,193,200,220],"labeled":[45],"source":[46,201],"view":[47,61],"predict":[49],"time":[51],"segments":[52],"descriptions":[54],"of":[55,141,173,222],"action":[56],"sequences":[57],"for":[58,117,192],"target":[60,203],"without":[62],"annotations.":[63],"Despite":[64],"previous":[65],"works":[66],"endeavoring":[67],"address":[69],"fully-supervised":[71],"single-view":[72],"or":[73],"cross-view":[74],"dense":[75],"video":[76],"captioning,":[77],"they":[78],"lapse":[79],"in":[80],"proposed":[82],"task":[83],"due":[84],"significant":[87],"inter-view":[88],"gap":[89],"caused":[90],"temporal":[92,179,195],"misalignment":[93],"irrelevant":[95],"object":[96],"interference.":[97],"Hence,":[98],"Gaze":[102,155],"Consensus-guided":[103],"Adaptation":[105],"Network":[106],"(GCEAN)":[107],"that":[108,131],"injects":[109],"gaze":[111,162,190],"information":[112],"into":[113],"learned":[115,167],"representations":[116,148,168],"fine-grained":[119],"alignment.":[121],"Specifically,":[122],"Score-based":[126],"Adversarial":[127],"Learning":[128],"Module":[129,158],"(SALM)":[130],"incorporates":[132],"discriminative":[134],"scoring":[135],"network":[136],"compares":[138],"scores":[140],"distinct":[142],"views":[143],"learn":[145],"unified":[146],"view-invariant":[147],"global":[151],"level.":[152],"Then,":[153],"Consensus":[156],"Construction":[157],"(GCCM)":[159],"utilizes":[160],"progressively":[164],"calibrate":[165],"highlight":[170],"regions":[172],"interest":[174],"extract":[176],"corresponding":[178],"contexts.":[180],"Moreover,":[181],"adopt":[183],"hierarchical":[184],"gaze-guided":[185],"consistency":[186],"losses":[187],"construct":[189],"consensus":[191],"explicit":[194],"spatial":[197],"adaptation":[198],"views.":[204],"To":[205],"support":[206],"our":[207,223],"research,":[208],"new":[212],"EgoMe-UE^2":[213],"DPAC":[214],"benchmark,":[215],"extensive":[217],"experiments":[218],"demonstrate":[219],"effectiveness":[221],"method,":[224],"outperforms":[226],"many":[227],"related":[228],"methods":[229],"large":[232],"margin.":[233],"Code":[234],"is":[235],"available":[236],"at":[237],"https://github.com/ZhaofengSHI/GCEAN.":[238]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}