{"id":"https://openalex.org/W4402473571","doi":"https://doi.org/10.1109/ispds62779.2024.10667513","title":"Enhance Image-to-Image Generation with LLaVA-generated Prompts","display_name":"Enhance Image-to-Image Generation with LLaVA-generated Prompts","publication_year":2024,"publication_date":"2024-05-31","ids":{"openalex":"https://openalex.org/W4402473571","doi":"https://doi.org/10.1109/ispds62779.2024.10667513"},"language":"en","primary_location":{"id":"doi:10.1109/ispds62779.2024.10667513","doi":"https://doi.org/10.1109/ispds62779.2024.10667513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispds62779.2024.10667513","pdf_url":null,"source":{"id":"https://openalex.org/S7407088239","display_name":"International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.01956","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104285922","display_name":"Zhicheng Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhicheng Ding","raw_affiliation_strings":["Columbia University,Fu Foundation School of Engineering and Applied Science,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Fu Foundation School of Engineering and Applied Science,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047800787","display_name":"Panfeng Li","orcid":"https://orcid.org/0000-0001-8586-0648","observed_orcids":["https://orcid.org/0000-0001-8586-0648"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panfeng Li","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100577167","display_name":"Qikai Yang","orcid":"https://orcid.org/0009-0009-8796-2387","observed_orcids":["https://orcid.org/0009-0009-8796-2387"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qikai Yang","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Computer Science,Urbana,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Computer Science,Urbana,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108960871","display_name":"Siyang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126863827","display_name":"Pace University","ror":"https://ror.org/047p7y759","country_code":"US","type":"education","lineage":["https://openalex.org/I126863827"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyang Li","raw_affiliation_strings":["Pace University,Lubin School of Business,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pace University,Lubin School of Business,New York,USA","institution_ids":["https://openalex.org/I126863827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1991,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95914924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"81"},"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":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0005000000237487257,"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/T14254","display_name":"Digital Media and Visual Art","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/image-to-image-generation","display_name":"image-to-image generation","score":0.9929999709129333},{"id":"https://openalex.org/keywords/llava","display_name":"LLaVA","score":0.9710000157356262},{"id":"https://openalex.org/keywords/prompt-generation","display_name":"prompt generation","score":0.6100000143051147},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7160000205039978},{"id":"https://openalex.org/keywords/image-similarity","display_name":"image similarity","score":0.8050000071525574},{"id":"https://openalex.org/keywords/visual-coherence","display_name":"visual coherence","score":0.8519999980926514}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.60739666223526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6005663275718689},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49786949157714844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46748086810112},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36777085065841675}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ispds62779.2024.10667513","doi":"https://doi.org/10.1109/ispds62779.2024.10667513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispds62779.2024.10667513","pdf_url":null,"source":{"id":"https://openalex.org/S7407088239","display_name":"International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.01956","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01956","pdf_url":"https://arxiv.org/pdf/2406.01956","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.01956","doi":"https://doi.org/10.48550/arxiv.2406.01956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.01956","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.01956","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01956","pdf_url":"https://arxiv.org/pdf/2406.01956","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402473571.pdf","grobid_xml":"https://content.openalex.org/works/W4402473571.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W3006871938","https://openalex.org/W3129576130","https://openalex.org/W3134763859","https://openalex.org/W3182770586","https://openalex.org/W4206399361","https://openalex.org/W4252086475","https://openalex.org/W4283838088","https://openalex.org/W4312933868","https://openalex.org/W4381327166","https://openalex.org/W4382318425","https://openalex.org/W4387432250","https://openalex.org/W4390843414","https://openalex.org/W4390873030","https://openalex.org/W4390873935","https://openalex.org/W4391306640","https://openalex.org/W4391409518","https://openalex.org/W4392781403","https://openalex.org/W4393284416","https://openalex.org/W4394913658","https://openalex.org/W4394998407","https://openalex.org/W4395443217","https://openalex.org/W4398787685","https://openalex.org/W4399544028","https://openalex.org/W4399885365","https://openalex.org/W4399885374","https://openalex.org/W4401608887","https://openalex.org/W4402353148","https://openalex.org/W4402353191","https://openalex.org/W4402527450","https://openalex.org/W4402713107","https://openalex.org/W4402727764","https://openalex.org/W4402811581","https://openalex.org/W4403421504","https://openalex.org/W4404295145","https://openalex.org/W4415799278","https://openalex.org/W6857610615","https://openalex.org/W6862519860","https://openalex.org/W6911093822","https://openalex.org/W7102410168","https://openalex.org/W7133193597"],"related_works":["https://openalex.org/W4402996555","https://openalex.org/W7164051736","https://openalex.org/W4406121929","https://openalex.org/W4410714727","https://openalex.org/W4408417217","https://openalex.org/W4417284694","https://openalex.org/W4414463945","https://openalex.org/W7140077772","https://openalex.org/W6979294503","https://openalex.org/W4403942908"],"abstract_inverted_index":{"This":[0,53],"paper":[1],"presents":[2],"a":[3,25,64,85,128],"novel":[4],"approach":[5],"to":[6,67,99,126,133],"enhance":[7],"image-to-image":[8,50],"generation":[9,51,58],"by":[10],"leveraging":[11],"the":[12,16,43,49,57,68,74,89,93,113,122,134,141],"multimodal":[13],"capabilities":[14],"of":[15,76],"Large":[17],"Language":[18],"and":[19,32,95,137],"Vision":[20],"Assistant":[21],"(LLaVA).":[22],"We":[23,83],"propose":[24],"framework":[26],"where":[27],"LLaVA":[28,107],"analyzes":[29],"input":[30,69,96],"images":[31,97],"generates":[33],"textual":[34],"descriptions,":[35],"hereinafter":[36],"LLaVA-generated":[37,77],"prompts.":[38],"These":[39],"prompts,":[40,123],"along":[41],"with":[42],"original":[44,135],"image,":[45],"are":[46],"fed":[47],"into":[48],"pipeline.":[52],"enriched":[54],"representation":[55],"guides":[56],"process":[59],"towards":[60],"outputs":[61],"that":[62],"exhibit":[63],"stronger":[65],"resemblance":[66],"image.":[70],"Extensive":[71],"experiments":[72],"demonstrate":[73],"effectiveness":[75],"prompts":[78,108],"in":[79,88,140],"promoting":[80],"image":[81,136],"similarity.":[82],"observe":[84],"significant":[86],"improvement":[87],"visual":[90],"coherence":[91],"between":[92,131],"generated":[94,142],"compared":[98],"traditional":[100],"methods.":[101],"Future":[102],"work":[103],"will":[104],"explore":[105],"fine-tuning":[106],"for":[109],"increased":[110],"control":[111],"over":[112],"creative":[114],"process.":[115],"By":[116],"providing":[117],"more":[118],"specific":[119],"details":[120],"within":[121],"we":[124],"aim":[125],"achieve":[127],"delicate":[129],"balance":[130],"faithfulness":[132],"artistic":[138],"expression":[139],"outputs.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":18}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-09-13T00:00:00"}