{"id":"https://openalex.org/W4414360297","doi":"https://doi.org/10.24963/ijcai.2025/654","title":"Find and Perceive: Tell Visual Change with Fine-Grained Comparison","display_name":"Find and Perceive: Tell Visual Change with Fine-Grained Comparison","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360297","doi":"https://doi.org/10.24963/ijcai.2025/654"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/654","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5063288528","display_name":"Feixiao Lv","orcid":"https://orcid.org/0009-0009-5033-4870"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feixiao Lv","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences;","School of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706529","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-9350-3667"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences;","School of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013812973","display_name":"Lihua Jing","orcid":"https://orcid.org/0009-0005-6369-7890"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Jing","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences;","School of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067567400","display_name":"Lijun Liu","orcid":"https://orcid.org/0000-0001-5021-4128"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences;","School of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063288528"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26675225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5878","last_page":"5886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.5462999939918518,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.5462999939918518,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9172999858856201},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.698199987411499},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6216999888420105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6047999858856201},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5763000249862671},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.557699978351593},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5175999999046326},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4146000146865845}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9172999858856201},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.698199987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6216999888420105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C36391188","wikidata":"https://www.wikidata.org/wiki/Q1939117","display_name":"Semantic change","level":2,"score":0.26930001378059387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/654","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,40,70,88,96,104,126,137],"the":[3,11,75,84,92,101,106,110,118,124,127,132,135],"image":[4,139],"change":[5,35,51,58,152,165,179],"captioning":[6,59,166],"task":[7,29],"is":[8],"to":[9],"capture":[10],"differences":[12],"between":[13],"two":[14,31,71,128],"similar":[15],"images":[16],"and":[17,38,63,91,121,168,182],"describe":[18],"them":[19],"in":[20],"natural":[21],"language.":[22],"In":[23],"this":[24,28],"paper,":[25],"we":[26,54,159],"decompose":[27],"into":[30],"sub-problems,":[32],"i.e.,":[33,74],"fine-grained":[34,119],"feature":[36,52],"learning":[37,60],"discrimination":[39],"changed":[41,97],"regions.":[42,108],"Compared":[43],"with":[44],"existing":[45,178],"methods":[46,181],"which":[47,147],"only":[48],"focus":[49],"on":[50,163],"learning,":[53],"propose":[55],"a":[56,113],"novel":[57],"paradigm,":[61],"Find":[62],"Perceive":[64],"(F&amp;P).":[65],"Our":[66],"proposed":[67,174],"F&amp;P":[68,176],"consists":[69],"main":[72],"ideas,":[73],"Fine-Grained":[76],"Semantic":[77],"Change":[78],"Perception":[79],"(FGSCP)":[80],"module":[81],"for":[82,99,141,151],"improving":[83,100],"model's":[85,102],"perception":[86],"ability":[87],"subtle":[89],"changes":[90],"Weakly-Supervised":[93],"Discriminator":[94],"(WSD)":[95],"regions":[98,148],"sensitivity":[103],"localising":[105],"important":[107,150],"Specifically,":[109],"FGSCP":[111],"deploys":[112],"two-step":[114],"manner,":[115],"firstly":[116],"introducing":[117],"categorisation":[120],"then":[122],"enhancing":[123],"interaction":[125],"paired":[129],"images.":[130],"And":[131],"WSD":[133],"adopts":[134],"contributions":[136],"each":[138],"region":[140],"final":[142],"generated":[143],"captions,":[144],"accurately":[145],"indicating":[146],"are":[149],"captions":[153],"without":[154],"any":[155],"extra":[156],"annotations.":[157],"Finally,":[158],"conduct":[160],"extensive":[161],"experiments":[162],"four":[164],"datasets,":[167],"experimental":[169],"results":[170],"show":[171],"that":[172],"our":[173],"method":[175],"outperforms":[177],"caption":[180],"achieves":[183],"new":[184],"state-of-the-art":[185],"performance.":[186]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
