{"id":"https://openalex.org/W4322730933","doi":"https://doi.org/10.1109/tmm.2023.3251111","title":"InterREC: An Interpretable Method for Referring Expression Comprehension","display_name":"InterREC: An Interpretable Method for Referring Expression Comprehension","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4322730933","doi":"https://doi.org/10.1109/tmm.2023.3251111"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3251111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3251111","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5100329719","display_name":"Wenbin Wang","orcid":"https://orcid.org/0000-0001-9710-0136"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenbin Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9710-0136","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069777357","display_name":"Maurice Pagnucco","orcid":"https://orcid.org/0000-0001-7712-6646"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maurice Pagnucco","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002596064","display_name":"Chengpei Xu","orcid":"https://orcid.org/0000-0001-8860-7701"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengpei Xu","raw_affiliation_strings":["School of Minerals and Energy Resources Engineering, University of New South Wales, Kensington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8860-7701","affiliations":[{"raw_affiliation_string":"School of Minerals and Energy Resources Engineering, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041567418","display_name":"Yang Song","orcid":"https://orcid.org/0000-0003-1283-1672"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1283-1672","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60060299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"9330","last_page":"9342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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/T10028","display_name":"Topic Modeling","score":0.9811999797821045,"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/interpretability","display_name":"Interpretability","score":0.9009572267532349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8089492321014404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6890850067138672},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5995892882347107},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5705813765525818},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5498478412628174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5190663933753967},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4600870609283447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4463896155357361},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.43956151604652405},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42105960845947266},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24169471859931946}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9009572267532349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089492321014404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6890850067138672},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5995892882347107},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5705813765525818},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5498478412628174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5190663933753967},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4600870609283447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4463896155357361},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43956151604652405},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42105960845947266},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24169471859931946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3251111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3251111","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2159080219","https://openalex.org/W2194775991","https://openalex.org/W2250378130","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2561715562","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2770129969","https://openalex.org/W2799263800","https://openalex.org/W2803125506","https://openalex.org/W2876852810","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2946165673","https://openalex.org/W2952524542","https://openalex.org/W2960655175","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963518342","https://openalex.org/W2963735856","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2970641574","https://openalex.org/W2981663434","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2998356391","https://openalex.org/W3000313058","https://openalex.org/W3000326268","https://openalex.org/W3014611590","https://openalex.org/W3034360800","https://openalex.org/W3034772468","https://openalex.org/W3034984754","https://openalex.org/W3035268124","https://openalex.org/W3035497460","https://openalex.org/W3037533539","https://openalex.org/W3090449556","https://openalex.org/W3104152799","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3120329650","https://openalex.org/W3154435685","https://openalex.org/W3159619744","https://openalex.org/W3173192496","https://openalex.org/W3173909648","https://openalex.org/W3174004334","https://openalex.org/W3189279073","https://openalex.org/W3198016657","https://openalex.org/W4214490042","https://openalex.org/W4224304134","https://openalex.org/W4283802492","https://openalex.org/W4285192809","https://openalex.org/W4304080498","https://openalex.org/W4309181071","https://openalex.org/W4313145013","https://openalex.org/W6739901393","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6775188310","https://openalex.org/W6779473860","https://openalex.org/W6789909235","https://openalex.org/W6798805250","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4247136043","https://openalex.org/W4312407344","https://openalex.org/W4384115502","https://openalex.org/W2381031055","https://openalex.org/W2366070815"],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Comprehension":[2],"(REC)":[3],"aims":[4],"to":[5,14,24,79,101,118,148,168],"locate":[6],"the":[7,11,25,81,105,111,124,130,155,160,165,184,202,206],"target":[8],"object":[9],"in":[10,64,77,104,110,123,129],"image":[12,106,125],"according":[13],"a":[15,20,69,97,114,135,176],"referring":[16],"expression.":[17,131],"This":[18],"is":[19],"challenging":[21],"task":[22],"owing":[23],"need":[26],"for":[27,139],"understanding":[28],"both":[29],"natural":[30],"language":[31],"and":[32,35,107,113,126,152,158,201],"visual":[33],"information":[34],"interpretable":[36,171],"reasoning":[37,172,180],"between":[38,121],"them.":[39],"Most":[40],"existing":[41,196],"implicit":[42],"reasoning-based":[43,50,72,198],"REC":[44,51,199],"methods":[45,52],"lack":[46],"interpretability,":[47,63],"while":[48,60],"explicit":[49,71,179,197],"have":[53],"lower":[54],"accuracy.":[55],"To":[56],"achieve":[57,169],"competitive":[58],"accuracy":[59,194],"providing":[61],"adequate":[62],"this":[65],"work,":[66],"we":[67,86,133,174],"propose":[68],"novel":[70],"method":[73,191],"named":[74],"InterREC.":[75],"First,":[76],"order":[78,157],"address":[80],"challenge":[82],"of":[83,162],"multi-modal":[84],"understanding,":[85],"design":[87,134,175],"two":[88],"neural":[89],"network":[90],"modules":[91],"based":[92],"on":[93,183,187],"text-image":[94],"representation":[95],"learning:":[96],"Text-Region":[98],"Matching":[99,116],"Module":[100,117],"align":[102,119],"objects":[103,122],"noun":[108],"phrases":[109,128],"expression,":[112],"Text-Relation":[115],"relations":[120],"relational":[127],"Additionally,":[132],"Reasoning":[136],"Order":[137],"Tree":[138],"handling":[140],"complex":[141,146],"expressions,":[142],"which":[143],"can":[144],"reduce":[145,159],"expressions":[147],"multiple":[149],"object-relation-object":[150],"triplets":[151],"therefore":[153],"identify":[154],"inference":[156],"difficulty":[161],"reasoning.":[163],"At":[164],"same":[166],"time,":[167],"an":[170],"step,":[173],"Bayesian":[177],"Network-based":[178],"method.":[181],"Based":[182],"comparative":[185],"evaluation":[186],"various":[188],"datasets,":[189],"our":[190],"achieves":[192],"higher":[193],"than":[195],"methods,":[200],"visualization":[203],"results":[204],"demonstrate":[205],"method's":[207],"high":[208],"interpretability.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}