{"id":"https://openalex.org/W7137972202","doi":"https://doi.org/10.1609/aaai.v40i7.37419","title":"From Pixels to Logic: A Perception-Reasoning Decomposition Framework for Open-World Referring Expression Comprehension","display_name":"From Pixels to Logic: A Perception-Reasoning Decomposition Framework for Open-World Referring Expression Comprehension","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137972202","doi":"https://doi.org/10.1609/aaai.v40i7.37419"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i7.37419","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37419","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37419/41381","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/37419/41381","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101151037","display_name":"Lihong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lihong Huang","raw_affiliation_strings":["Shenzhen University, College of Computer Science and Software Engineering, Shenzhen, 518060, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, College of Computer Science and Software Engineering, Shenzhen, 518060, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086801574","display_name":"Sheng-hua Zhong","orcid":"https://orcid.org/0000-0002-7524-5999"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng-hua Zhong","raw_affiliation_strings":["Shenzhen University, College of Computer Science and Software Engineering, Shenzhen, 518060, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, College of Computer Science and Software Engineering, Shenzhen, 518060, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666948","display_name":"Zhi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhi Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Department of Computing, Hong Kong, 999077, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Department of Computing, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129681078","display_name":"Yan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Department of Computing, Hong Kong, 999077, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Department of Computing, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101151037"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21026372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5058","last_page":"5066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944000244140625,"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":0.9944000244140625,"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":0.000699999975040555,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.0005000000237487257,"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/inference","display_name":"Inference","score":0.6816999912261963},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.656499981880188},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5940999984741211},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.526199996471405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4262999892234802},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.40849998593330383}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7060999870300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937999725341797},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.574400007724762},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5339000225067139},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i7.37419","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37419","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37419/41381","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"},{"id":"pmh:oai:ojs.aaai.org:article/37419","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37419","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37419","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37419/41381","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/16","display_name":"Peace, Justice and strong institutions","score":0.7838298082351685}],"awards":[{"id":"https://openalex.org/G3895771356","display_name":null,"funder_award_id":"2025A1515012154","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7596153138","display_name":null,"funder_award_id":"62472291","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"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137972202.pdf","grobid_xml":"https://content.openalex.org/works/W7137972202.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,34,143],"Referring":[3],"Expression":[4],"Comprehension":[5],"(REC)":[6],"have":[7],"been":[8],"largely":[9],"driven":[10],"by":[11],"supervised":[12,173],"learning":[13],"on":[14,147],"curated":[15],"datasets,":[16],"where":[17,37],"each":[18],"expression":[19,127],"is":[20],"assumed":[21],"to":[22,24,41,45,47,94,123],"refer":[23,40,46],"exactly":[25],"one":[26],"known":[27],"object.":[28],"However,":[29],"such":[30],"assumptions":[31],"rarely":[32],"hold":[33],"real-world":[35],"scenarios,":[36],"expressions":[38],"can":[39],"multiple":[42],"objects,":[43],"fail":[44],"any,":[48],"or":[49],"involve":[50],"novel":[51],"categories":[52],"and":[53,68,128,140,160],"complex":[54],"semantics.":[55],"These":[56],"challenges":[57],"define":[58],"the":[59,72,102,125,134],"task":[60],"of":[61,74],"open-world":[62,96,144],"REC,":[63],"which":[64],"demands":[65],"robust":[66],"generalization":[67,142],"structured":[69],"reasoning":[70,93,120],"beyond":[71],"scope":[73],"traditional":[75],"REC":[76,150],"methods.":[77],"In":[78],"this":[79],"work,":[80],"we":[81],"introduce":[82],"a":[83,106,119],"novel,":[84],"training-free":[85],"framework":[86,165],"that":[87,163],"decouples":[88],"visual":[89,103],"perception":[90,114],"from":[91],"linguistic":[92],"address":[95],"REC.":[97],"Our":[98],"method":[99],"first":[100],"transforms":[101],"scene":[104],"into":[105],"rich":[107],"textual":[108],"representation":[109],"using":[110],"an":[111],"open-vocabulary":[112],"multimodal":[113],"module.":[115],"It":[116],"then":[117],"employs":[118],"language":[121],"model":[122],"interpret":[124],"referring":[126],"perform":[129],"explicit":[130],"logical":[131],"inference":[132],"over":[133],"perceived":[135],"scene,":[136],"enabling":[137],"transparent":[138],"decision-making":[139],"strong":[141],"scenarios.":[145],"Experiments":[146],"three":[148],"standard":[149],"benchmarks":[151],"as":[152,154],"well":[153],"two":[155],"more":[156],"challenging":[157],"ones,":[158],"gRefCOCO":[159],"D\u00b3,":[161],"demonstrate":[162],"our":[164],"achieves":[166],"highly":[167],"competitive":[168],"zero-shot":[169],"performance,":[170],"often":[171],"surpassing":[172],"baselines.":[174]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2026-03-18T00:00:00"}