{"id":"https://openalex.org/W4414770317","doi":"https://doi.org/10.1109/iccv51701.2025.01780","title":"VSC: Visual Search Compositional Text-to-Image Diffusion Model","display_name":"VSC: Visual Search Compositional Text-to-Image Diffusion Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414770317","doi":"https://doi.org/10.1109/iccv51701.2025.01780"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.01104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093367357","display_name":"Do Huu Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Do Huu Dat","raw_affiliation_strings":["VinUniversity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VinUniversity","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119824173","display_name":"Nam Hyeonu","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Hyeon-Woo","raw_affiliation_strings":["POSTECH,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Department of Electrical Engineering","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112024477","display_name":"Pei-Wen Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Yuan Mao","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["POSTECH,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Department of Electrical Engineering","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19153","last_page":"19162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.88919997215271,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.88919997215271,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.847100019454956,"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/robustness","display_name":"Robustness (evolution)","score":0.7092000246047974},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6499000191688538},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6468999981880188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6371999979019165},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6265000104904175},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4595000147819519},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110000252723694},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7092000246047974},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6468999981880188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6371999979019165},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558000206947327},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.01104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01104","pdf_url":"https://arxiv.org/pdf/2505.01104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2505.01104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.01104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.01104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01104","pdf_url":"https://arxiv.org/pdf/2505.01104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,156],"models":[2,157],"have":[3,60],"shown":[4],"impressive":[5],"capabilities":[6],"in":[7,26,144,179],"generating":[8],"realistic":[9],"visuals":[10],"from":[11,36],"natural-language":[12],"prompts,":[13],"yet":[14,82],"they":[15,83],"often":[16],"struggle":[17],"with":[18,87,126],"accurately":[19],"binding":[20,145,177],"attributes":[21,147],"to":[22,50,62,106,129,148],"corresponding":[23,118],"objects,":[24],"especially":[25],"prompts":[27,114],"containing":[28],"multiple":[29,146],"attribute-object":[30,108],"pairs.":[31],"This":[32],"challenge":[33],"primarily":[34],"arises":[35],"the":[37,73,159,180],"limitations":[38],"of":[39,75,176],"commonly":[40],"used":[41],"text":[42,127],"encoders,":[43],"such":[44],"as":[45],"CLIP,":[46],"which":[47],"can":[48],"fail":[49],"encode":[51],"complex":[52,113],"linguistic":[53],"relationships":[54],"and":[55,72,120,170],"modifiers":[56],"effectively.":[57],"Existing":[58],"approaches":[59,151],"attempted":[61],"mitigate":[63],"these":[64],"issues":[65],"through":[66],"attention":[67],"map":[68],"control":[69],"during":[70,80],"inference":[71],"use":[74],"layout":[76],"information":[77],"or":[78],"fine-tuning":[79],"training,":[81,136],"face":[84],"performance":[85],"drops":[86],"increased":[88],"prompt":[89],"complexity.":[90],"In":[91],"this":[92],"work,":[93],"we":[94,137],"introduce":[95],"a":[96],"novel":[97],"compositional":[98,154],"generation":[99],"method":[100],"that":[101,124],"leverages":[102],"pairwise":[103],"image":[104,165],"embeddings":[105,128],"improve":[107],"binding.":[109],"Our":[110,150],"approach":[111],"decomposes":[112],"into":[115],"sub-prompts,":[116],"generates":[117],"images,":[119],"computes":[121],"visual":[122],"prototypes":[123],"fuse":[125],"enhance":[130],"representation.":[131],"By":[132],"applying":[133],"segmentation-based":[134],"localization":[135],"address":[138],"cross-attention":[139],"misalignment,":[140],"achieving":[141,163],"improved":[142],"accuracy":[143],"objects.":[149],"outperform":[152],"existing":[153],"text-to-image":[155],"on":[158],"benchmark":[160],"T2I":[161],"CompBench,":[162],"better":[164],"quality,":[166],"evaluated":[167],"by":[168],"humans,":[169],"emerging":[171],"robustness":[172],"under":[173],"scaling":[174],"number":[175],"pairs":[178],"prompt.":[181]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}