{"id":"https://openalex.org/W2944466895","doi":"https://doi.org/10.48550/arxiv.1905.03743","title":"Interactive Image Generation Using Scene Graphs","display_name":"Interactive Image Generation Using Scene Graphs","publication_year":2019,"publication_date":"2019-05-09","ids":{"openalex":"https://openalex.org/W2944466895","doi":"https://doi.org/10.48550/arxiv.1905.03743","mag":"2944466895"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1905.03743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03743","pdf_url":"https://arxiv.org/pdf/1905.03743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.03743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067385304","display_name":"Gaurav Mittal","orcid":"https://orcid.org/0000-0002-6942-3891","observed_orcids":["https://orcid.org/0000-0002-6942-3891"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mittal, Gaurav","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh , PA 15213 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh , PA 15213 , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043008976","display_name":"Shubham Agrawal","orcid":"https://orcid.org/0000-0002-7017-5557","observed_orcids":["https://orcid.org/0000-0002-7017-5557"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agrawal, Shubham","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh , PA 15213 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh , PA 15213 , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012037385","display_name":"Anuva Agarwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agarwal, Anuva","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh , PA 15213 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh , PA 15213 , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027547345","display_name":"Sushant Mehta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehta, Sushant","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh , PA 15213 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh , PA 15213 , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051269909","display_name":"Tanya Marwah","orcid":"https://orcid.org/0000-0001-5436-2355","observed_orcids":["https://orcid.org/0000-0001-5436-2355"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marwah, Tanya","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh , PA 15213 , USA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh , PA 15213 , USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9926999807357788,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9926999807357788,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0071000000461936,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scene-graph","display_name":"scene graph","score":0.9520000219345093},{"id":"https://openalex.org/keywords/scene-graph-generation","display_name":"scene graph generation","score":0.3919999897480011},{"id":"https://openalex.org/keywords/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.8600000143051147},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.8989999890327454},{"id":"https://openalex.org/keywords/image-to-image-translation","display_name":"image-to-image translation","score":0.5550000071525574},{"id":"https://openalex.org/keywords/multi-object-images","display_name":"multi-object images","score":0.8090000152587891},{"id":"https://openalex.org/keywords/coco-stuff","display_name":"COCO-Stuff","score":0.8040000200271606},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.4740000069141388},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6048837900161743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5586832761764526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.545231819152832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48979902267456055},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44110867381095886}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1905.03743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03743","pdf_url":"https://arxiv.org/pdf/1905.03743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1905.03743","doi":"https://doi.org/10.48550/arxiv.1905.03743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.03743","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2965505993","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr1905.html#abs-1905-03743","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.03743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03743","pdf_url":"https://arxiv.org/pdf/1905.03743","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944466895.pdf","grobid_xml":"https://content.openalex.org/works/W2944466895.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2099471712","https://openalex.org/W2405756170","https://openalex.org/W2432004435","https://openalex.org/W2506483933","https://openalex.org/W2564591810","https://openalex.org/W2766091292","https://openalex.org/W2790214987","https://openalex.org/W2891802882","https://openalex.org/W2949376505","https://openalex.org/W2950053619","https://openalex.org/W2962785568","https://openalex.org/W2963184176","https://openalex.org/W2963565467","https://openalex.org/W2963966654","https://openalex.org/W2964216930","https://openalex.org/W2979672901","https://openalex.org/W3203023649"],"related_works":["https://openalex.org/W2963184176","https://openalex.org/W3191104361","https://openalex.org/W4403602825","https://openalex.org/W7133233171","https://openalex.org/W7160941506","https://openalex.org/W4200311227","https://openalex.org/W2973045729","https://openalex.org/W6959943806","https://openalex.org/W4409367216","https://openalex.org/W2943259397"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,19],"witnessed":[3],"some":[4],"exciting":[5],"developments":[6],"in":[7,36,100,176],"the":[8,63,96,105,110,160,173],"domain":[9],"of":[10,82,84],"generating":[11,23,34,177],"images":[12,24,35,139,155,180],"from":[13,25],"scene-based":[14],"text":[15,28,53],"descriptions.":[16],"These":[17],"approaches":[18,171],"primarily":[20],"focused":[21],"on":[22,49,79,172],"a":[26,37,71,80,90],"static":[27],"description":[29,54],"and":[30,60,103,163],"are":[31,41],"limited":[32],"to":[33,43,62,73,122,124,135],"single":[38],"pass.":[39],"They":[40],"unable":[42],"generate":[44,74,136],"an":[45,50,67,75],"image":[46,76,97,107,132],"interactively":[47],"based":[48,78],"incrementally":[51,77,182],"additive":[52],"(something":[55],"that":[56,94,165],"is":[57],"more":[58],"intuitive":[59],"similar":[61],"way":[64],"we":[65],"describe":[66],"image).":[68],"We":[69,88,147],"propose":[70,89],"method":[72],"sequence":[81],"graphs":[83,127],"scene":[85,113,126,162,184],"descriptions":[86],"(scene-graphs).":[87],"recurrent":[91],"network":[92],"architecture":[93],"preserves":[95],"content":[98],"generated":[99],"previous":[101],"steps":[102],"modifies":[104],"cumulative":[106],"as":[108],"per":[109],"newly":[111],"provided":[112],"information.":[114],"Our":[115],"model":[116,167],"utilizes":[117],"Graph":[118],"Convolutional":[119],"Networks":[120],"(GCN)":[121],"cater":[123],"variable-sized":[125],"along":[128,156],"with":[129,149,157],"Generative":[130],"Adversarial":[131],"translation":[133],"networks":[134],"realistic":[137],"multi-object":[138,154],"without":[140],"needing":[141],"any":[142],"intermediate":[143],"supervision":[144],"during":[145],"training.":[146],"experiment":[148],"Coco-Stuff":[150],"dataset":[151,175],"which":[152],"has":[153],"annotations":[158],"describing":[159],"visual":[161],"show":[164],"our":[166],"significantly":[168],"outperforms":[169],"other":[170],"same":[174],"visually":[178],"consistent":[179],"for":[181],"growing":[183],"graphs.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-05-16T00:00:00"}