{"id":"https://openalex.org/W4313406113","doi":"https://doi.org/10.1109/tip.2022.3226624","title":"One-Stage Visual Relationship Referring With Transformers and Adaptive Message Passing","display_name":"One-Stage Visual Relationship Referring With Transformers and Adaptive Message Passing","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4313406113","doi":"https://doi.org/10.1109/tip.2022.3226624","pmid":"https://pubmed.ncbi.nlm.nih.gov/37015479"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3226624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3226624","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100459499","display_name":"Hang Wang","orcid":"https://orcid.org/0000-0001-9876-8285"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Wang","raw_affiliation_strings":["Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-9876-8285","affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074080669","display_name":"Youtian Du","orcid":"https://orcid.org/0000-0002-1714-3433"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youtian Du","raw_affiliation_strings":["Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-1714-3433","affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681562","display_name":"Yabin Zhang","orcid":"https://orcid.org/0000-0003-3380-2870"},"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":"Yabin Zhang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424119","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0003-0760-5267"},"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":"Shuai Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-0760-5267","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433899","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2078-4215"},"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":"Lei Zhang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2078-4215","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54586572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"190","last_page":"202"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261052131652832},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6619012951850891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.572946310043335},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5324398279190063},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.521141529083252},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5178018808364868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48880812525749207},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4762404263019562},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4327578544616699},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24468526244163513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261052131652832},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6619012951850891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.572946310043335},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5324398279190063},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.521141529083252},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5178018808364868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48880812525749207},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4762404263019562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4327578544616699},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24468526244163513},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3226624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3226624","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37015479","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37015479","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2701289319","display_name":null,"funder_award_id":"2018AAA0101501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1985585937","https://openalex.org/W2108598243","https://openalex.org/W2127795553","https://openalex.org/W2131774270","https://openalex.org/W2160254296","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2591644541","https://openalex.org/W2795378892","https://openalex.org/W2904910963","https://openalex.org/W2908510526","https://openalex.org/W2933775054","https://openalex.org/W2951193251","https://openalex.org/W2955014993","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2962779575","https://openalex.org/W2963650529","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2999606372","https://openalex.org/W3006154882","https://openalex.org/W3009131631","https://openalex.org/W3010803012","https://openalex.org/W3034538190","https://openalex.org/W3034772468","https://openalex.org/W3035017890","https://openalex.org/W3036686441","https://openalex.org/W3096609285","https://openalex.org/W3107593279","https://openalex.org/W3110435696","https://openalex.org/W3111980808","https://openalex.org/W3133684245","https://openalex.org/W3160447289","https://openalex.org/W3174293538","https://openalex.org/W3185066916","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4287728378","https://openalex.org/W4289126595","https://openalex.org/W4293584584","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6678830454","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6757135208","https://openalex.org/W6757817989","https://openalex.org/W6765369709","https://openalex.org/W6778485988","https://openalex.org/W6780226713","https://openalex.org/W6780471797"],"related_works":["https://openalex.org/W2369744843","https://openalex.org/W4379011373","https://openalex.org/W3196658210","https://openalex.org/W2756241593","https://openalex.org/W192715707","https://openalex.org/W4213376880","https://openalex.org/W2897098896","https://openalex.org/W2767280493","https://openalex.org/W4280560571","https://openalex.org/W2949768986"],"abstract_inverted_index":{"There":[0],"exist":[1],"a":[2,13,68,95,101,125,161,196,210],"variety":[3],"of":[4,25,34,52,70,97,104,114,176,222],"visual":[5,26,142],"relationships":[6],"among":[7],"entities":[8,46,71,98],"in":[9,47],"an":[10,48,117,136,181,188,223],"image.":[11,49],"Given":[12],"relationship":[14,27,143],"query":[15],"$\\langle":[16],"subject,":[17],"predicate,":[18],"object":[19,45],"\\rangle":[20],"$":[21],",":[22],"the":[23,35,42,73,83,112,152,167,173,205,219,227,231,234,258],"task":[24,113],"referring":[28],"(VRR)":[29],"aims":[30],"to":[31,92,150,165,171,195],"disambiguate":[32],"instances":[33],"same":[36],"entity":[37,224],"category":[38],"and":[39,44,60,123,135,145,186,233,240,253],"simultaneously":[40],"localize":[41,67,93],"subject":[43],"Previous":[50],"works":[51,203],"VRR":[53,115],"can":[54],"be":[55],"generally":[56],"categorized":[57],"into":[58,160],"one-stage":[59,127,251],"multi-stage":[61,260],"methods.":[62,261],"The":[63,214],"former":[64],"ones":[65,85],"directly":[66],"pair":[69],"from":[72,78,209],"image":[74],"but":[75,88],"they":[76,89],"suffer":[77],"low":[79],"prediction":[80],"accuracy,":[81],"while":[82],"latter":[84],"perform":[86],"better":[87],"are":[90,147,157],"indirect":[91],"only":[94],"couple":[96],"by":[99,131,225],"pre-generating":[100],"rich":[102],"amount":[103],"candidate":[105],"proposals.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,179],"formulate":[111],"as":[116],"end-to-end":[118],"bounding":[119],"box":[120],"regression":[121],"problem":[122],"propose":[124],"novel":[126],"approach,":[128],"called":[129],"VRR-TAMP,":[130],"effectively":[132],"integrating":[133],"Transformers":[134],"adaptive":[137,182],"message":[138,183,198],"passing":[139,184,199],"mechanism.":[140],"First,":[141],"queries":[144],"images":[146],"respectively":[148],"encoded":[149],"generate":[151],"basic":[153],"modality-specific":[154],"embeddings,":[155],"which":[156,193],"then":[158],"fed":[159],"cross-modal":[162],"Transformer":[163],"encoder":[164],"produce":[166],"joint":[168,206],"representation.":[169],"Second,":[170],"obtain":[172],"specific":[174],"representation":[175,207,221],"each":[177],"entity,":[178],"introduce":[180],"mechanism":[185],"design":[187],"entity-specific":[189],"information":[190],"distiller":[191],"SR-GMP,":[192],"refers":[194],"gated":[197],"(GMP)":[200],"module":[201,216],"that":[202,245],"on":[204,238],"learned":[208],"single":[211],"learnable":[212],"token.":[213],"GMP":[215],"adaptively":[217],"distills":[218],"final":[220],"incorporating":[226],"contextual":[228],"cues":[229],"regarding":[230],"predicate":[232],"other":[235],"entity.":[236],"Experiments":[237],"VRD":[239],"Visual":[241],"Genome":[242],"datasets":[243],"demonstrate":[244],"our":[246],"approach":[247],"significantly":[248],"outperforms":[249],"its":[250],"competitors":[252],"achieves":[254],"competitive":[255],"results":[256],"with":[257],"state-of-the-art":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}