{"id":"https://openalex.org/W4379382409","doi":"https://doi.org/10.1109/tpami.2023.3282889","title":"Constrained Structure Learning for Scene Graph Generation","display_name":"Constrained Structure Learning for Scene Graph Generation","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379382409","doi":"https://doi.org/10.1109/tpami.2023.3282889","pmid":"https://pubmed.ncbi.nlm.nih.gov/37276097"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3282889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3282889","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5035562985","display_name":"Daqi Liu","orcid":"https://orcid.org/0000-0002-0475-581X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Daqi Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-0475-581X","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030037960","display_name":"Miros\u0142aw Bober","orcid":"https://orcid.org/0000-0001-9484-9125"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miroslaw Bober","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9484-9125","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8110-9205","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"The authors are with the Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035562985"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.6485,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85960951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"45","issue":"10","first_page":"11588","last_page":"11599"},"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":0.9955000281333923,"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":0.994700014591217,"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/inference","display_name":"Inference","score":0.7766100168228149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294842004776001},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5393519401550293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302070379257202},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.528974711894989},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4851978123188019},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.42551618814468384},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4152663052082062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40413397550582886},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3984208405017853},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2889561355113983}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7766100168228149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294842004776001},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5393519401550293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302070379257202},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.528974711894989},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4851978123188019},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.42551618814468384},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4152663052082062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40413397550582886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3984208405017853},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2889561355113983},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3282889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3282889","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37276097","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37276097","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1026162944","display_name":"(N00014-16-R-FO05) Semantic Information Pursuit for Multimodal Data Analysis","funder_award_id":"EP/R018456/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2886788793","display_name":null,"funder_award_id":"JADE2 (EP/T022205/1)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7111890331","display_name":null,"funder_award_id":"EP/V002856/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G764753648","display_name":null,"funder_award_id":"EP/R018456/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G993479927","display_name":null,"funder_award_id":"MVSE (EP/V002856/1)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1515020792","https://openalex.org/W1686810756","https://openalex.org/W1766290689","https://openalex.org/W1971945429","https://openalex.org/W2009274429","https://openalex.org/W2016384870","https://openalex.org/W2039466093","https://openalex.org/W2105842272","https://openalex.org/W2116341502","https://openalex.org/W2136634080","https://openalex.org/W2172174689","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2521028896","https://openalex.org/W2579549467","https://openalex.org/W2607855566","https://openalex.org/W2745461083","https://openalex.org/W2788537604","https://openalex.org/W2810482788","https://openalex.org/W2886970679","https://openalex.org/W2922277163","https://openalex.org/W2948672349","https://openalex.org/W2950096400","https://openalex.org/W2955988340","https://openalex.org/W2962779575","https://openalex.org/W2962785943","https://openalex.org/W2962933664","https://openalex.org/W2963091558","https://openalex.org/W2963101956","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963938081","https://openalex.org/W2969679616","https://openalex.org/W2986758741","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3081642947","https://openalex.org/W3106328333","https://openalex.org/W3152893301","https://openalex.org/W3173181410","https://openalex.org/W3174865181","https://openalex.org/W3181556077","https://openalex.org/W3196936439","https://openalex.org/W4288083516","https://openalex.org/W4293052541","https://openalex.org/W4301435544","https://openalex.org/W4312563197","https://openalex.org/W4312578903","https://openalex.org/W4366352717","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6675783020","https://openalex.org/W6677388865","https://openalex.org/W6683825394","https://openalex.org/W6686565794","https://openalex.org/W6694738858","https://openalex.org/W6736685754","https://openalex.org/W6754554023","https://openalex.org/W6754684146","https://openalex.org/W6767384042"],"related_works":["https://openalex.org/W2785442381","https://openalex.org/W2189749715","https://openalex.org/W2372267530","https://openalex.org/W1614580364","https://openalex.org/W2215785064","https://openalex.org/W2978729728","https://openalex.org/W3103344181","https://openalex.org/W2752328056","https://openalex.org/W2770224089","https://openalex.org/W2159992248"],"abstract_inverted_index":{"As":[0],"a":[1,11,53,81,103],"structured":[2],"prediction":[3],"task,":[4],"scene":[5,13,131],"graph":[6,14,132],"generation":[7,133],"aims":[8],"to":[9,15,62,115],"build":[10],"visually-grounded":[12],"explicitly":[16],"model":[17,127],"objects":[18],"and":[19,67,135],"their":[20],"relationships":[21],"in":[22,43],"an":[23,88],"input":[24],"image.":[25],"Currently,":[26],"the":[27,34,40,45,70,99,117,124,140],"mean":[28],"field":[29],"variational":[30,91,119],"Bayesian":[31],"framework":[32],"is":[33,49,94,113],"de":[35],"facto":[36],"methodology":[37],"used":[38],"by":[39,52],"existing":[41],"methods,":[42],"which":[44,87],"unconstrained":[46],"inference":[47,65,92,120],"step":[48],"often":[50],"implemented":[51],"message":[54],"passing":[55],"neural":[56],"network.":[57],"However,":[58],"such":[59],"formulation":[60],"fails":[61],"explore":[63],"other":[64],"strategies,":[66],"largely":[68],"ignores":[69],"more":[71],"general":[72],"constrained":[73,82,90,105,118],"optimization":[74,106],"models.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"present":[80],"structure":[83],"learning":[84],"method,":[85],"for":[86],"explicit":[89],"objective":[93],"proposed.":[95],"Instead":[96],"of":[97],"applying":[98],"ubiquitous":[100],"message-passing":[101],"strategy,":[102],"generic":[104,126],"method":[107],"-":[108,112],"entropic":[109],"mirror":[110],"descent":[111],"utilized":[114],"solve":[116],"step.":[121],"We":[122],"validate":[123],"proposed":[125],"on":[128],"various":[129],"popular":[130],"benchmarks":[134],"show":[136],"that":[137],"it":[138],"outperforms":[139],"state-of-the-art":[141],"methods.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}