{"id":"https://openalex.org/W7138013549","doi":"https://doi.org/10.1609/aaai.v40i11.37907","title":"Manipulation Intention Understanding for Zero-Shot Composed Image Retrieval","display_name":"Manipulation Intention Understanding for Zero-Shot Composed Image Retrieval","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138013549","doi":"https://doi.org/10.1609/aaai.v40i11.37907"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37907","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37907","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37907/41869","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/37907/41869","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129724411","display_name":"Yuanmin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanmin Tang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677732","display_name":"Jing Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":["Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China\nSchool of Information Engineering, Minzu University of China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China\nSchool of Information Engineering, Minzu University of China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722189","display_name":"Keke Gai","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Gai","raw_affiliation_strings":["School of AI, Beijing Institute of Technology, Beijing 100081, China\nZhongguancun Academy, Haidian, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of AI, Beijing Institute of Technology, Beijing 100081, China\nZhongguancun Academy, Haidian, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656069","display_name":"Gang Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Xiong","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739841","display_name":"Gaopeng Gou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaopeng Gou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences\nSchool of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718920","display_name":"Meikang Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087454","display_name":"Augusta University Health","ror":"https://ror.org/007rawr89","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meikang Qiu","raw_affiliation_strings":["School of Computer and Cyber Sciences Augusta University Augusta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer and Cyber Sciences Augusta University Augusta, Georgia, USA","institution_ids":["https://openalex.org/I4210087454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129725760","display_name":"Qi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2802355861","display_name":"Australian Institute of Business","ror":"https://ror.org/01wf5jq34","country_code":"AU","type":"education","lineage":["https://openalex.org/I2802355861"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Responsible AI Research Centre, Adelaide University"],"affiliations":[{"raw_affiliation_string":"Responsible AI Research Centre, Adelaide University","institution_ids":["https://openalex.org/I2802355861"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129724411"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28943452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9466","last_page":"9474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9261000156402588,"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":0.9261000156402588,"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":0.013199999928474426,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.010700000450015068,"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/inference","display_name":"Inference","score":0.6495000123977661},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6251999735832214},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5971999764442444},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.492900013923645},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.477400004863739},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4318999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808899998664856},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.492900013923645},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37907","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37907","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37907/41869","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.v40i11.37907","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37907","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37907/41869","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":[],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138013549.pdf","grobid_xml":"https://content.openalex.org/works/W7138013549.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"Composed":[1],"Image":[2],"Retrieval":[3],"(ZS-CIR)":[4],"involves":[5],"diverse":[6],"tasks":[7],"with":[8,107,153],"varied":[9],"visual":[10],"manipulation":[11,65,85,109],"intents":[12],"across":[13],"domains,":[14],"scenes,":[15],"objects,":[16],"and":[17,87,104,123,140],"attributes.":[18],"A":[19,94],"key":[20],"challenge":[21],"is":[22],"that":[23,77],"existing":[24,143],"datasets":[25],"contain":[26],"limited":[27],"intent-relevant":[28],"annotations,":[29],"making":[30],"it":[31,106,125],"hard":[32],"for":[33,63,129],"models":[34,62],"to":[35,58,83,111,147],"infer":[36],"human":[37,64],"intent":[38,66,86],"from":[39,120],"textual":[40],"modifications.":[41],"We":[42],"introduce":[43],"an":[44],"intent-centric":[45],"image\u2013text":[46],"dataset":[47],"generated":[48],"via":[49],"reasoning":[50,81],"by":[51,145],"a":[52,75,113],"Multimodal":[53],"Large":[54],"Language":[55],"Model":[56],"(MLLM)":[57],"better":[59],"train":[60],"ZS-CIR":[61,134],"understanding.":[67],"Building":[68],"on":[69],"this":[70,121],"dataset,":[71],"we":[72],"propose":[73],"De-MINDS,":[74],"framework":[76],"distills":[78],"the":[79,108],"MLLM\u2019s":[80],"ability":[82],"capture":[84],"enhance":[88],"models\u2019":[89],"comprehension":[90],"of":[91],"modified":[92],"text.":[93],"simple":[95],"mapping":[96],"network":[97],"translates":[98],"image":[99],"information":[100,119],"into":[101],"language":[102],"space":[103],"combines":[105],"text":[110],"form":[112],"query.":[114],"De-MINDS":[115,136],"then":[116],"extracts":[117],"intention-relevant":[118],"query":[122],"encodes":[124],"as":[126],"pseudo-word":[127],"tokens":[128],"accurate":[130],"ZS-CIR.":[131],"Across":[132],"four":[133],"tasks,":[135],"shows":[137],"strong":[138],"generalization":[139],"improves":[141],"over":[142],"methods":[144],"2.15%":[146],"4.05%,":[148],"establishing":[149],"new":[150],"state-of-the-art":[151],"results":[152],"comparable":[154],"inference":[155],"time.":[156]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}