{"id":"https://openalex.org/W4206516739","doi":"https://doi.org/10.1145/3469877.3490601","title":"Hierarchical Composition Learning for Composed Query Image Retrieval","display_name":"Hierarchical Composition Learning for Composed Query Image Retrieval","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4206516739","doi":"https://doi.org/10.1145/3469877.3490601"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3490601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014129038","display_name":"Yahui Xu","orcid":"https://orcid.org/0000-0002-1123-6129"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Xu","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334018","display_name":"Guoqing Wang","orcid":"https://orcid.org/0000-0002-3938-5994"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Wang","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, CN","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.78461092710495},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6365455389022827},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5652438998222351},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5643920302391052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5539113283157349},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5392853617668152},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4886181950569153},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48641538619995117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4753539264202118},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4687155783176422},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4679590165615082},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4672562777996063},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41914379596710205},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.41546037793159485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13208124041557312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78461092710495},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6365455389022827},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5652438998222351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5643920302391052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539113283157349},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5392853617668152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4886181950569153},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48641538619995117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4753539264202118},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4687155783176422},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4679590165615082},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4672562777996063},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41914379596710205},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.41546037793159485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13208124041557312},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469877.3490601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1948251820","https://openalex.org/W2012210378","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2591669147","https://openalex.org/W2745461083","https://openalex.org/W2752667240","https://openalex.org/W2752674409","https://openalex.org/W2752930373","https://openalex.org/W2765440071","https://openalex.org/W2766724094","https://openalex.org/W2803620531","https://openalex.org/W2884326683","https://openalex.org/W2887712318","https://openalex.org/W2904323922","https://openalex.org/W2905544595","https://openalex.org/W2907166662","https://openalex.org/W2952866723","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2964138017","https://openalex.org/W2964211610","https://openalex.org/W2979667596","https://openalex.org/W2981448404","https://openalex.org/W3003735286","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3037773948","https://openalex.org/W3092782803","https://openalex.org/W3092962760","https://openalex.org/W3169472988","https://openalex.org/W3180476551","https://openalex.org/W3205604798"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2147874738","https://openalex.org/W2036058638","https://openalex.org/W2513891871"],"abstract_inverted_index":{"Composed":[0],"query":[1,97],"image":[2,146,166,183],"retrieval":[3],"is":[4,11,55,85,131],"a":[5,148,185,201],"growing":[6],"research":[7],"topic.":[8],"The":[9],"object":[10],"to":[12,25,64,87,181,205],"retrieve":[13],"images":[14,116],"not":[15,61],"only":[16,62],"generally":[17],"resemble":[18],"the":[19,26,50,78,89,96,111,145,168,174,192],"reference":[20,45,165],"image,":[21],"but":[22,73],"differ":[23],"according":[24],"desired":[27],"modification":[28,35,53,162,179],"text.":[29],"Existing":[30],"methods":[31],"mainly":[32],"explore":[33,206],"composing":[34],"text":[36,54,163,180],"with":[37,77,147],"global":[38,66,90],"feature":[39,67,176],"or":[40,68,91],"local":[41,70,92],"entity":[42,71,93,123,208],"descriptor":[43],"of":[44,121,191],"image.":[46],"However,":[47],"they":[48],"ignore":[49],"fact":[51],"that":[52],"indeed":[56],"diverse":[57],"and":[58,124,142,164,209,217],"arbitrary.":[59],"It":[60,171],"relates":[63],"abstractive":[65],"concrete":[69],"transformation,":[72],"also":[74],"often":[75],"associates":[76],"fine-grained":[79],"structured":[80],"visual":[81,94,175],"adjustment.":[82],"Thus,":[83],"it":[84],"insufficient":[86],"emphasize":[88],"for":[95],"composition.":[98],"In":[99],"this":[100,104],"work,":[101],"we":[102,154,199],"tackle":[103],"task":[105],"by":[106,160],"hierarchical":[107,157],"composition":[108,158],"learning.":[109],"Specifically,":[110],"proposed":[112],"method":[113],"first":[114],"encodes":[115],"into":[117],"three":[118,196],"representations":[119],"consisting":[120],"global,":[122,207],"structure":[125,210],"level":[126,129],"representations.":[127],"Structure":[128],"representation":[130],"richly":[132],"explicable,":[133],"which":[134,188,212],"explicitly":[135],"describes":[136],"entities":[137],"as":[138,140],"well":[139],"attributes":[141],"relationships":[143],"in":[144,167,184],"directed":[149],"graph.":[150],"Based":[151],"on":[152,178],"these,":[153],"naturally":[155],"perform":[156],"learning":[159],"fusing":[161],"global-entity-structure":[169],"manner.":[170],"can":[172,213],"transform":[173],"conditioned":[177],"target":[182],"coarse-to-fine":[186],"manner,":[187],"takes":[189],"advantage":[190],"complementary":[193],"information":[194],"among":[195],"levels.":[197],"Moreover,":[198],"introduce":[200],"hybrid":[202],"space":[203],"matching":[204],"alignments":[211],"get":[214],"high":[215],"performance":[216],"good":[218],"interpretability.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}