{"id":"https://openalex.org/W7137953310","doi":"https://doi.org/10.1609/aaai.v40i16.38423","title":"Decoupling What to Count and Where to See for Referring Expression Counting","display_name":"Decoupling What to Count and Where to See for Referring Expression Counting","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137953310","doi":"https://doi.org/10.1609/aaai.v40i16.38423"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38423","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38423","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38423/42385","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38423/42385","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108885723","display_name":"Yuda Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuda Zou","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129751628","display_name":"Zijian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129727884","display_name":"Yongchao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongchao Xu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Hubei Luojia Laboratory, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108885723"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20610119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"14113","last_page":"14121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38989999890327454,"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":0.38989999890327454,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.09139999747276306,"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/T10028","display_name":"Topic Modeling","score":0.07129999995231628,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/focus","display_name":"Focus (optics)","score":0.6866999864578247},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.607200026512146},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.5184000134468079},{"id":"https://openalex.org/keywords/subclass","display_name":"Subclass","score":0.5131000280380249},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.49230000376701355}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.607200026512146},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5286999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195000171661377},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C2776194381","wikidata":"https://www.wikidata.org/wiki/Q3965271","display_name":"Subclass","level":3,"score":0.5131000280380249},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41179999709129333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38423","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38423","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38423/42385","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38423","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38423","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38423/42385","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.61711186170578}],"awards":[{"id":"https://openalex.org/G142741563","display_name":null,"funder_award_id":"62222112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6366742431","display_name":null,"funder_award_id":"62176186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7174558747","display_name":null,"funder_award_id":"Group","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137953310.pdf","grobid_xml":"https://content.openalex.org/works/W7137953310.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Counting":[2],"(REC)":[3],"extends":[4],"class-level":[5,50],"object":[6],"counting":[7,158],"to":[8,13,47,80,84,112,141],"the":[9,23,76,92,99,151,154],"fine-grained":[10],"subclass-level,":[11],"aiming":[12],"enumerate":[14],"objects":[15],"matching":[16,134],"a":[17,70,87,132,138],"textual":[18],"expression":[19],"that":[20,73,97,136],"specifies":[21],"both":[22],"class":[24],"and":[25,82,114,163,166,172],"distinguishing":[26],"attribute.":[27],"A":[28],"fundamental":[29],"challenge,":[30],"however,":[31],"has":[32],"been":[33],"overlooked:":[34],"annotation":[35],"points":[36],"are":[37,110],"typically":[38],"placed":[39],"on":[40,49,153],"class-representative":[41],"locations":[42],"(e.g.,":[43,60],"heads),":[44],"forcing":[45],"models":[46],"focus":[48],"features":[51,116],"while":[52],"neglecting":[53],"attribute":[54],"information":[55],"from":[56,117],"other":[57],"visual":[58,119],"regions":[59],"legs":[61],"for":[62],"''walking'').":[63],"To":[64],"address":[65],"this,":[66],"we":[67,101,126],"propose":[68],"W2-Net,":[69],"novel":[71,133],"framework":[72],"explicitly":[74],"decouples":[75],"problem":[77],"into":[78],"''what":[79],"count''":[81],"''where":[83],"see''":[85],"via":[86],"dual-query":[88],"mechanism.":[89],"Specifically,":[90],"alongside":[91],"standard":[93],"what-to-count":[94],"(w2c)":[95],"queries":[96,109],"localize":[98],"object,":[100],"introduce":[102,127],"dedicated":[103],"where-to-see":[104],"(w2s)":[105],"queries.":[106],"The":[107],"w2s":[108],"guided":[111],"seek":[113],"extract":[115],"attribute-specific":[118],"regions,":[120],"enabling":[121],"precise":[122],"subclass":[123],"discrimination.":[124],"Furthermore,":[125],"Subclass":[128],"Separable":[129],"Matching":[130],"(SSM),":[131],"strategy":[135],"incorporates":[137],"repulsive":[139],"force":[140],"enhance":[142],"inter-subclass":[143],"separability":[144],"during":[145],"label":[146],"assignment.":[147],"W2-Net":[148],"significantly":[149],"outperforms":[150],"state-of-the-art":[152],"REC-8K":[155],"dataset,":[156],"reducing":[157],"error":[159],"by":[160,170],"22.5%":[161],"(validation)":[162],"18.0%":[164],"(test),":[165],"improving":[167],"localization":[168],"F1":[169],"7%":[171],"8%,":[173],"respectively.":[174]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}
