{"id":"https://openalex.org/W7138390763","doi":"https://doi.org/10.1609/aaai.v40i10.37742","title":"Imagine with Layout and Sketch: Enhancing Vision-Language Retrieval with Dual-Stream Multi-Modal Query Refinement","display_name":"Imagine with Layout and Sketch: Enhancing Vision-Language Retrieval with Dual-Stream Multi-Modal Query Refinement","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138390763","doi":"https://doi.org/10.1609/aaai.v40i10.37742"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37742","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37742","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37742/41704","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37742/41704","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102398518","display_name":"Guanghao Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"GuangHao Meng","raw_affiliation_strings":["Tsinghua University\nPengcheng Laborotary"],"affiliations":[{"raw_affiliation_string":"Tsinghua University\nPengcheng Laborotary","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723335","display_name":"Jinpeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686283","display_name":"Qian-Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian-Wei Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073114321","display_name":"Xudong Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XuDong Ren","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129666918","display_name":"Dan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Zhao","raw_affiliation_strings":["Pengcheng Laborotary"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laborotary","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102398518"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73645681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7972","last_page":"7980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908999800682068,"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":0.9908999800682068,"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":0.0035000001080334187,"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":0.000699999975040555,"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/leverage","display_name":"Leverage (statistics)","score":0.6680999994277954},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6664000153541565},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4027999937534332},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38449999690055847},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.3750999867916107},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.3587000072002411},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.33869999647140503},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3314000070095062},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597000241279602},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6680999994277954},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3971000015735626},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37742","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37742","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37742/41704","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37742","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37742","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37742/41704","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1838801417","display_name":null,"funder_award_id":"201405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138390763.pdf","grobid_xml":"https://content.openalex.org/works/W7138390763.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Retrieval":[1],"(VLR)":[2],"aims":[3],"to":[4,32,136,175],"retrieve":[5],"relevant":[6],"visual":[7,138],"or":[8,16],"textual":[9],"information":[10],"from":[11],"multimodal":[12,71],"data":[13],"using":[14,172],"language":[15],"image":[17],"queries.":[18],"However,":[19,124],"traditional":[20],"VLR":[21,63,197],"methods":[22],"often":[23],"rely":[24],"on":[25,47,186],"data-driven":[26],"shallow":[27],"semantic":[28,108],"alignment":[29],"and":[30,37,50,60,73,113,132,140,205],"fail":[31],"understand":[33],"the":[34,58,80,148,179,193],"deeper":[35],"structural":[36,94],"fine-grained":[38,117],"entity":[39,89],"features":[40],"of":[41,83,156],"queries,":[42],"resulting":[43],"in":[44],"poor":[45],"performance":[46,198],"multi-entity":[48],"layouts":[49],"challenging":[51],"entities.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,101,146],"propose":[57,147],"Layout-Aware":[59],"Sketch-Enhanced":[61],"(LASE)":[62],"framework,":[64],"which":[65,154],"refines":[66,88],"query":[67,187],"representations":[68],"by":[69,91],"incorporating":[70],"layout":[72,77,111],"sketch":[74,86,122],"knowledge.":[75],"Specifically,":[76],"knowledge":[78,87,99,126,141,171,183],"encodes":[79],"spatial":[81],"arrangement":[82],"entities,":[84],"while":[85,178],"perception":[90],"capturing":[92],"essential":[93],"details.":[95],"To":[96,143],"extract":[97],"these":[98],"representations,":[100],"leverage":[102],"Large":[103],"Language":[104],"Models'":[105,115],"(LLMs)":[106],"powerful":[107],"understanding":[109],"for":[110,121],"generation,":[112],"Diffusion":[114],"(DMs)":[116],"cross-modal":[118],"generative":[119],"capabilities":[120],"generation.":[123],"integrating":[125],"into":[127],"queries":[128],"may":[129],"introduce":[130],"biases":[131],"query-specific":[133],"preferences":[134],"due":[135],"varying":[137],"content":[139],"demands.":[142],"address":[144],"this,":[145],"Gated":[149],"Dual-Stream":[150],"Knowledge":[151],"Module":[152],"(GDKM),":[153],"consists":[155],"a":[157,162],"multi-instance":[158],"fusion":[159,167],"network":[160,168,181],"with":[161,202],"sample-aware":[163],"gating":[164,180],"network.":[165],"The":[166],"aggregates":[169],"diverse":[170],"multi-head":[173],"attention":[174],"reduce":[176],"bias,":[177],"adjusts":[182],"weights":[184],"based":[185],"characteristics.":[188],"Extensive":[189],"experiments":[190],"demonstrate":[191],"that":[192],"LASE":[194],"significantly":[195],"enhances":[196],"across":[199],"multiple":[200],"benchmarks,":[201],"superior":[203],"generalization":[204],"transferability.":[206]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}