{"id":"https://openalex.org/W3206369173","doi":"https://doi.org/10.1145/3474085.3475677","title":"Exploring Logical Reasoning for Referring Expression Comprehension","display_name":"Exploring Logical Reasoning for Referring Expression Comprehension","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206369173","doi":"https://doi.org/10.1145/3474085.3475677","mag":"3206369173"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060790908","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-9103-6126"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002746311","display_name":"Ruize Wang","orcid":"https://orcid.org/0000-0001-6281-4091"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruize Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052798964","display_name":"Jiashuo Yu","orcid":"https://orcid.org/0000-0002-3094-6687"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626035","display_name":"Rui-Wei Zhao","orcid":"https://orcid.org/0000-0002-8498-5761"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Wei Zhao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5047","last_page":"5055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9958999752998352,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7845523953437805},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.749962568283081},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.683550238609314},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6343749761581421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6073288917541504},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.594038724899292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.572414219379425},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5636995434761047},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.506754457950592},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48831674456596375},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"Logical reasoning","score":0.45897191762924194},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4205816984176636},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15185192227363586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09636750817298889}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845523953437805},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.749962568283081},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.683550238609314},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6343749761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6073288917541504},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.594038724899292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.572414219379425},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5636995434761047},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.506754457950592},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48831674456596375},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.45897191762924194},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4205816984176636},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15185192227363586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09636750817298889},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2250532017","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2296268288","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2617995259","https://openalex.org/W2725395424","https://openalex.org/W2745461083","https://openalex.org/W2770129969","https://openalex.org/W2799263800","https://openalex.org/W2908242605","https://openalex.org/W2923924002","https://openalex.org/W2949276121","https://openalex.org/W2952524542","https://openalex.org/W2960655175","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2963115613","https://openalex.org/W2963290083","https://openalex.org/W2963687836","https://openalex.org/W2964345792","https://openalex.org/W2964935470","https://openalex.org/W2970746059","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2998356391","https://openalex.org/W3037533539","https://openalex.org/W3112077297"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2088988140","https://openalex.org/W2103019253","https://openalex.org/W2951529875","https://openalex.org/W2391453316","https://openalex.org/W2297768894","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"Referring":[0],"expression":[1,52,114],"comprehension":[2,53],"aims":[3],"to":[4,46,62,81,92],"localize":[5],"the":[6,22,83,104,117],"target":[7],"object":[8],"in":[9,54,66,103],"an":[10],"image":[11],"referred":[12],"by":[13,97],"a":[14,43,55],"natural":[15],"language":[16],"expression.":[17],"Most":[18],"existing":[19,94],"approaches":[20],"neglect":[21],"implicit":[23],"logical":[24,48,73,79],"correlations":[25],"among":[26],"fine-grained":[27,64],"cues,":[28],"e.g.,":[29],"categories,":[30],"attributes,":[31],"which":[32],"are":[33,109],"beneficial":[34],"for":[35,50],"distinguishing":[36],"objects.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,60,90],"propose":[42,61,91],"logic-guided":[44],"approach":[45],"explore":[47],"knowledge":[49],"referring":[51,113],"hierarchical":[56],"modular-based":[57,95],"framework.":[58],"Specifically,":[59],"extract":[63],"cues":[65],"visual":[67],"and":[68,71,116,128],"textual":[69],"domains":[70],"perform":[72],"reasoning":[74],"over":[75],"them":[76],"with":[77,134],"explicit":[78],"expressions":[80],"regularize":[82],"matching":[84],"process":[85],"without":[86],"extra":[87],"parameters.":[88],"Besides,":[89],"improve":[93],"methods":[96],"introducing":[98],"context":[99],"information":[100],"of":[101],"objects":[102],"relationship":[105],"module.":[106],"Extensive":[107],"experiments":[108],"conducted":[110],"on":[111],"three":[112],"datasets,":[115],"results":[118],"demonstrate":[119],"that":[120],"our":[121],"model":[122],"can":[123],"produce":[124],"more":[125],"consistent":[126],"predictions":[127],"further":[129],"achieve":[130],"superior":[131],"performance":[132],"compared":[133],"previous":[135],"methods.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}