{"id":"https://openalex.org/W4388145690","doi":"https://doi.org/10.1109/tpami.2023.3329339","title":"Importance Weighted Structure Learning for Scene Graph Generation","display_name":"Importance Weighted Structure Learning for Scene Graph Generation","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4388145690","doi":"https://doi.org/10.1109/tpami.2023.3329339","pmid":"https://pubmed.ncbi.nlm.nih.gov/37910406"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3329339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3329339","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/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]},{"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":["School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K","Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]},{"raw_affiliation_string":"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"],"affiliations":[{"raw_affiliation_string":"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"],"affiliations":[{"raw_affiliation_string":"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/I153648349","https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.4779,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65797922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"46","issue":"2","first_page":"1231","last_page":"1242"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9843999743461609,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.983299970626831,"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/softmax-function","display_name":"Softmax function","score":0.8138510584831238},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6140410304069519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6046472191810608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985920429229736},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5657141804695129},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5120766758918762},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.46624723076820374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4423035979270935},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4347493052482605},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4279954731464386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37312090396881104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34847491979599},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3207300901412964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2783588767051697}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8138510584831238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6140410304069519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6046472191810608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985920429229736},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5657141804695129},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5120766758918762},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.46624723076820374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4423035979270935},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4347493052482605},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4279954731464386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37312090396881104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34847491979599},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3207300901412964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2783588767051697},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3329339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3329339","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:37910406","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37910406","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":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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/G1595280774","display_name":"JADE: Joint Academic Data science Endeavour - 2","funder_award_id":"EP/T022205/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6868706350","display_name":"Multimodal Video Search by Examples (MVSE)","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/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"}],"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":56,"referenced_works":["https://openalex.org/W35586085","https://openalex.org/W1766290689","https://openalex.org/W1971945429","https://openalex.org/W2009274429","https://openalex.org/W2016384870","https://openalex.org/W2039466093","https://openalex.org/W2116341502","https://openalex.org/W2136634080","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2339172597","https://openalex.org/W2547875792","https://openalex.org/W2579549467","https://openalex.org/W2607855566","https://openalex.org/W2745461083","https://openalex.org/W2798836702","https://openalex.org/W2810482788","https://openalex.org/W2886970679","https://openalex.org/W2948672349","https://openalex.org/W2955988340","https://openalex.org/W2962779575","https://openalex.org/W2962785943","https://openalex.org/W2962851448","https://openalex.org/W2962933664","https://openalex.org/W2963084599","https://openalex.org/W2963091558","https://openalex.org/W2963101956","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2963902384","https://openalex.org/W2963938081","https://openalex.org/W2969679616","https://openalex.org/W2986758741","https://openalex.org/W2990257819","https://openalex.org/W3034538190","https://openalex.org/W3034601242","https://openalex.org/W3035017890","https://openalex.org/W3035342001","https://openalex.org/W3152893301","https://openalex.org/W3181556077","https://openalex.org/W3196936439","https://openalex.org/W4214693531","https://openalex.org/W4288083516","https://openalex.org/W4293052541","https://openalex.org/W4312563197","https://openalex.org/W4312578903","https://openalex.org/W6620707391","https://openalex.org/W6638116569","https://openalex.org/W6730091202","https://openalex.org/W6736685754","https://openalex.org/W6754554023","https://openalex.org/W6764733053"],"related_works":["https://openalex.org/W2189749715","https://openalex.org/W3103344181","https://openalex.org/W2987799900","https://openalex.org/W4226287370","https://openalex.org/W2114556850","https://openalex.org/W42646284","https://openalex.org/W2070797946","https://openalex.org/W2752328056","https://openalex.org/W2770224089","https://openalex.org/W2159992248"],"abstract_inverted_index":{"Scene":[0],"graph":[1,21,148],"generation":[2,81,149],"is":[3,38,52,110,127],"a":[4,18,44,88,103,117],"structured":[5],"prediction":[6],"task":[7],"aiming":[8,95],"to":[9,55,79,96,129],"explicitly":[10],"model":[11],"objects":[12],"and":[13],"their":[14],"relationships":[15],"via":[16],"constructing":[17],"visually-grounded":[19],"scene":[20,147],"for":[22,42],"an":[23],"input":[24],"image.":[25],"Currently,":[26],"the":[27,39,48,57,63,73,98,131,141],"message":[28],"passing":[29],"neural":[30],"network":[31],"based":[32],"mean":[33],"field":[34],"variational":[35,49,64,134],"Bayesian":[36],"methodology":[37],"ubiquitous":[40],"solution":[41],"such":[43,68],"task,":[45],"in":[46],"which":[47,76,109],"inference":[50,135],"objective":[51,70],"often":[53,77],"assumed":[54],"be":[56],"classical":[58],"evidence":[59],"lower":[60,107],"bound.":[61],"However,":[62],"approximation":[65],"inferred":[66],"from":[67,112,116],"loose":[69],"generally":[71],"underestimates":[72],"underlying":[74,99],"posterior,":[75],"leads":[78],"inferior":[80],"performance.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"novel":[89],"importance":[90,105],"weighted":[91,106],"structure":[92],"learning":[93],"method":[94,139],"approximate":[97],"log-partition":[100],"function":[101],"with":[102],"tighter":[104],"bound,":[108],"computed":[111],"multiple":[113],"samples":[114],"drawn":[115],"reparameterizable":[118],"Gumbel-Softmax":[119],"sampler.":[120],"A":[121],"generic":[122],"entropic":[123],"mirror":[124],"descent":[125],"algorithm":[126],"applied":[128],"solve":[130],"resulting":[132],"constrained":[133],"task.":[136],"The":[137],"proposed":[138],"achieves":[140],"state-of-the-art":[142],"performance":[143],"on":[144],"various":[145],"popular":[146],"benchmarks.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}