{"id":"https://openalex.org/W3163567431","doi":"https://doi.org/10.1109/icpr48806.2021.9413251","title":"Exploring and Exploiting the Hierarchical Structure of a Scene for Scene Graph Generation","display_name":"Exploring and Exploiting the Hierarchical Structure of a Scene for Scene Graph Generation","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163567431","doi":"https://doi.org/10.1109/icpr48806.2021.9413251","mag":"3163567431"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5077819796","display_name":"Ikuto Kurosawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ikuto Kurosawa","raw_affiliation_strings":["Waseda university, Tokyo, JAPAN"],"affiliations":[{"raw_affiliation_string":"Waseda university, Tokyo, JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda university, Tokyo, JAPAN"],"affiliations":[{"raw_affiliation_string":"Waseda university, Tokyo, JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101814461","display_name":"Yoshihiko Hayashi","orcid":"https://orcid.org/0000-0002-1682-1976"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Hayashi","raw_affiliation_strings":["Waseda university, Tokyo, JAPAN"],"affiliations":[{"raw_affiliation_string":"Waseda university, Tokyo, JAPAN","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077819796"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05053922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":null,"first_page":"1422","last_page":"1429"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/scene-graph","display_name":"Scene graph","score":0.8325810432434082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010427355766296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5965355038642883},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5065001249313354},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.48677587509155273},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45799097418785095},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4477531611919403},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43833598494529724},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4056386351585388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3896576762199402},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20878934860229492}],"concepts":[{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.8325810432434082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010427355766296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5965355038642883},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5065001249313354},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.48677587509155273},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45799097418785095},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4477531611919403},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43833598494529724},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4056386351585388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3896576762199402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20878934860229492},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2077069816","https://openalex.org/W2131774270","https://openalex.org/W2132914434","https://openalex.org/W2251939518","https://openalex.org/W2277195237","https://openalex.org/W2309415944","https://openalex.org/W2519887557","https://openalex.org/W2547875792","https://openalex.org/W2579549467","https://openalex.org/W2613718673","https://openalex.org/W2811124557","https://openalex.org/W2886970679","https://openalex.org/W2939208918","https://openalex.org/W2951659295","https://openalex.org/W2953106684","https://openalex.org/W2962779575","https://openalex.org/W2963150697","https://openalex.org/W2963175980","https://openalex.org/W2963184176","https://openalex.org/W2963449176","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2964015378","https://openalex.org/W2989377923","https://openalex.org/W4295750171","https://openalex.org/W6620707391","https://openalex.org/W6631782140","https://openalex.org/W6639824700","https://openalex.org/W6691459498","https://openalex.org/W6753331806","https://openalex.org/W6753998590","https://openalex.org/W6754554023"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2070401501","https://openalex.org/W2121496884","https://openalex.org/W4387129494"],"abstract_inverted_index":{"The":[0,130],"scene":[1,39,51,57,148],"graph":[2,58,149],"of":[3,11,49,103,110],"an":[4,7],"image":[5],"is":[6,61,68,88,118],"explicit,":[8],"concise":[9],"representation":[10],"the":[12,47,53,56,83,91,95,107,111,115,121,127,134,140,144,157,162],"image;":[13],"hence,":[14],"it":[15],"can":[16],"be":[17,167],"used":[18,69],"in":[19,55,82,147],"various":[20],"applications":[21],"such":[22],"as":[23],"visual":[24],"question":[25],"answering":[26],"or":[27],"robot":[28],"vision.":[29],"We":[30,152],"propose":[31],"a":[32,72,86],"novel":[33],"neural":[34],"network":[35],"model":[36,67,142,164],"for":[37],"generating":[38],"graphs":[40],"that":[41,139,156],"maintain":[42,125],"global":[43,116],"consistency,":[44],"which":[45],"prevents":[46],"generation":[48,59,150],"unrealistic":[50],"graphs;":[52],"performance":[54],"task":[60],"expected":[62],"to":[63,70,79,120,124,166],"improve.":[64],"Our":[65],"proposed":[66,141,163],"construct":[71],"hierarchical":[73,112,158],"structure":[74,93],"whose":[75],"leaf":[76],"nodes":[77],"correspond":[78],"objects":[80,105],"depicted":[81],"image,":[84],"and":[85,114],"message":[87],"passed":[89],"along":[90],"estimated":[92],"on":[94,133],"fly.":[96],"To":[97],"this":[98],"end,":[99],"we":[100],"aggregate":[101],"features":[102],"all":[104,126],"into":[106],"root":[108,122],"node":[109,123],"structure,":[113],"context":[117],"back-propagated":[119],"object":[128],"nodes.":[129],"experimental":[131],"results":[132],"Visual":[135],"Genome":[136],"dataset":[137],"indicate":[138],"outperformed":[143],"existing":[145],"models":[146],"tasks.":[151],"further":[153],"qualitatively":[154],"confirmed":[155],"structures":[159],"captured":[160],"by":[161],"seemed":[165],"valid.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}