{"id":"https://openalex.org/W3201861986","doi":"https://doi.org/10.1109/iccv48922.2021.01563","title":"Context-aware Scene Graph Generation with Seq2Seq Transformers","display_name":"Context-aware Scene Graph Generation with Seq2Seq Transformers","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3201861986","doi":"https://doi.org/10.1109/iccv48922.2021.01563","mag":"3201861986"},"language":"en","primary_location":{"id":"doi:10.1109/iccv48922.2021.01563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01563","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-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/A5089283502","display_name":"Yichao Lu","orcid":"https://orcid.org/0009-0001-2005-1724"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yichao Lu","raw_affiliation_strings":["Layer 6 AI"],"affiliations":[{"raw_affiliation_string":"Layer 6 AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084346046","display_name":"Himanshu Rai","orcid":"https://orcid.org/0000-0003-4768-3817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himanshu Rai","raw_affiliation_strings":["Layer 6 AI"],"affiliations":[{"raw_affiliation_string":"Layer 6 AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016135743","display_name":"Jason S. Chang","orcid":"https://orcid.org/0000-0002-8227-7382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Chang","raw_affiliation_strings":["Layer 6 AI"],"affiliations":[{"raw_affiliation_string":"Layer 6 AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054351253","display_name":"B. A. Knyazev","orcid":"https://orcid.org/0000-0003-4187-3249"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Boris Knyazev","raw_affiliation_strings":["University of Guelph,School of Engineering","School of Engineering, University of Guelph","Vector Institute for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Guelph,School of Engineering","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"School of Engineering, University of Guelph","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054686849","display_name":"Guangwei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangwei Yu","raw_affiliation_strings":["Layer 6 AI"],"affiliations":[{"raw_affiliation_string":"Layer 6 AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763873","display_name":"Shashank Shekhar","orcid":"https://orcid.org/0000-0001-8934-7171"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shashank Shekhar","raw_affiliation_strings":["University of Guelph,School of Engineering","Vector Institute for Artificial Intelligence","School of Engineering, University of Guelph"],"affiliations":[{"raw_affiliation_string":"University of Guelph,School of Engineering","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"School of Engineering, University of Guelph","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922725","display_name":"Graham W. Taylor","orcid":"https://orcid.org/0000-0001-5867-3652"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Graham W. Taylor","raw_affiliation_strings":["University of Guelph,School of Engineering","School of Engineering, University of Guelph","Vector Institute for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Guelph,School of Engineering","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"School of Engineering, University of Guelph","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027341076","display_name":"Maksims Volkovs","orcid":"https://orcid.org/0009-0007-0561-2187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maksims Volkovs","raw_affiliation_strings":["Layer 6 AI"],"affiliations":[{"raw_affiliation_string":"Layer 6 AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089283502"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.986,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.95607719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15911","last_page":"15921"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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":0.9955000281333923,"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":0.8240669965744019},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6303834319114685},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6186648011207581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5651159286499023},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5272861123085022},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5215611457824707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.511987030506134},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45185816287994385},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35898923873901367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240669965744019},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6303834319114685},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6186648011207581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651159286499023},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5272861123085022},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5215611457824707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.511987030506134},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45185816287994385},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35898923873901367},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv48922.2021.01563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01563","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W2016589492","https://openalex.org/W2077069816","https://openalex.org/W2155027007","https://openalex.org/W2257979135","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2629538667","https://openalex.org/W2777602943","https://openalex.org/W2882995289","https://openalex.org/W2883170015","https://openalex.org/W2886970679","https://openalex.org/W2928869317","https://openalex.org/W2947385066","https://openalex.org/W2949718784","https://openalex.org/W2953106684","https://openalex.org/W2955988340","https://openalex.org/W2962737704","https://openalex.org/W2962785943","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963314968","https://openalex.org/W2963403868","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963650529","https://openalex.org/W2963902384","https://openalex.org/W2963938081","https://openalex.org/W2963980128","https://openalex.org/W2964121744","https://openalex.org/W2966204614","https://openalex.org/W2966608828","https://openalex.org/W2969679616","https://openalex.org/W2987123286","https://openalex.org/W2990397898","https://openalex.org/W2992478697","https://openalex.org/W2995985914","https://openalex.org/W2997514790","https://openalex.org/W3010715592","https://openalex.org/W3024031618","https://openalex.org/W3025726122","https://openalex.org/W3025915648","https://openalex.org/W3030520226","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3042550126","https://openalex.org/W3081642947","https://openalex.org/W3094502228","https://openalex.org/W3106328333","https://openalex.org/W3108864070","https://openalex.org/W3109229205","https://openalex.org/W3119150707","https://openalex.org/W3122411985","https://openalex.org/W3128099838","https://openalex.org/W3170630188","https://openalex.org/W3173181410","https://openalex.org/W3174865181","https://openalex.org/W3205051885","https://openalex.org/W4214685694","https://openalex.org/W4287724527","https://openalex.org/W4287728378","https://openalex.org/W4287815368","https://openalex.org/W4288286281","https://openalex.org/W4297733535","https://openalex.org/W4298395628","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6683204974","https://openalex.org/W6721769334","https://openalex.org/W6739901393","https://openalex.org/W6739930931","https://openalex.org/W6752937567","https://openalex.org/W6753369936","https://openalex.org/W6753998590","https://openalex.org/W6763119976","https://openalex.org/W6763367864","https://openalex.org/W6765591853","https://openalex.org/W6766545348","https://openalex.org/W6771806749","https://openalex.org/W6772344733","https://openalex.org/W6776424751","https://openalex.org/W6776977327","https://openalex.org/W6777585808","https://openalex.org/W6777613640","https://openalex.org/W6778485988","https://openalex.org/W6780471797","https://openalex.org/W6781022920","https://openalex.org/W6784333009","https://openalex.org/W6788354309","https://openalex.org/W6794636349"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Scene":[0],"graph":[1,129,147],"generation":[2],"is":[3,212],"an":[4,83,102],"important":[5],"task":[6],"in":[7,42,82,98,200],"computer":[8],"vision":[9],"aimed":[10],"at":[11,79],"improving":[12],"the":[13,17,23,37,63,69,90,109,127,165,171],"semantic":[14],"understanding":[15],"of":[16,36,202],"visual":[18,31,76],"world.":[19],"In":[20,133],"this":[21,210],"task,":[22],"model":[24,74,104],"needs":[25],"to":[26,52,144],"detect":[27],"objects":[28],"and":[29,114,169,175,204],"predict":[30,40],"relationships":[32,41,77],"between":[33,173],"them.":[34],"Most":[35],"existing":[38],"models":[39,97],"parallel":[43],"assuming":[44],"their":[45],"independence.":[46],"While":[47],"there":[48],"are":[49],"different":[50],"ways":[51],"capture":[53],"these":[54],"dependencies,":[55],"we":[56,100,135,161],"explore":[57],"a":[58,80,137,151],"conditional":[59],"approach":[60,156,189],"motivated":[61],"by":[62,86,124],"sequence-to-sequence":[64],"(Seq2Seq)":[65],"formalism.":[66],"Different":[67],"from":[68,95],"previous":[70,195],"research,":[71],"our":[72,186],"proposed":[73],"predicts":[75],"one":[78],"time":[81],"autoregressive":[84],"manner":[85],"explicitly":[87],"conditioning":[88,125],"on":[89,126,179],"already":[91],"predicted":[92],"relationships.":[93],"Drawing":[94],"translation":[96],"NLP,":[99],"propose":[101],"encoder-decoder":[103],"built":[105],"using":[106,150],"Transformers":[107],"where":[108],"encoder":[110],"captures":[111],"global":[112],"context":[113],"long":[115],"range":[116],"interactions.":[117],"The":[118],"decoder":[119],"then":[120],"makes":[121],"sequential":[122],"predictions":[123],"scene":[128,146],"constructed":[130],"so":[131],"far.":[132],"addition,":[134],"introduce":[136],"novel":[138],"reinforcement":[139],"learning-based":[140],"training":[141,155,174,203],"strategy":[142],"tailored":[143],"Seq2Seq":[145,187],"generation.":[148],"By":[149],"self-critical":[152],"policy":[153],"gradient":[154],"with":[157],"Monte":[158],"Carlo":[159],"search":[160],"directly":[162],"optimize":[163],"for":[164,209],"(mean)":[166],"recall":[167],"metrics":[168],"bridge":[170],"gap":[172],"evaluation.":[176],"Experimental":[177],"results":[178],"two":[180],"public":[181],"benchmark":[182],"datasets":[183],"demonstrate":[184],"that":[185],"learning":[188],"achieves":[190],"strong":[191],"empirical":[192],"performance,":[193],"outperforming":[194],"state-of-the-art,":[196],"while":[197],"remaining":[198],"efficient":[199],"terms":[201],"inference":[205],"time.":[206],"Full":[207],"code":[208],"work":[211],"available":[213],"here:":[214],"https://github.com/layer6ai-labs/SGG-Seq2Seq.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}