{"id":"https://openalex.org/W3205173298","doi":"https://doi.org/10.1145/3474085.3475619","title":"Image Search with Text Feedback by Deep Hierarchical Attention Mutual Information Maximization","display_name":"Image Search with Text Feedback by Deep Hierarchical Attention Mutual Information Maximization","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205173298","doi":"https://doi.org/10.1145/3474085.3475619","mag":"3205173298"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5112882352","display_name":"Chunbin Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunbin Gu","raw_affiliation_strings":["Zhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["Zhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390140","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0001-7871-7405"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["Zhejiang UniversityZhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang UniversityZhejiang University & Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006367063","display_name":"Zhi Yu","orcid":"https://orcid.org/0000-0003-2305-0492"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024477428","display_name":"Dongfang Ma","orcid":"https://orcid.org/0000-0002-9334-1570"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongfang Ma","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757829","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8598-0831"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4600","last_page":"4609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10824","display_name":"Image Retrieval and Classification 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/mutual-information","display_name":"Mutual information","score":0.8011487722396851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423179149627686},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6334620714187622},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.608013927936554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5834905505180359},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5272746682167053},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4875625967979431},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4543461501598358},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41969162225723267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1363106667995453}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.8011487722396851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423179149627686},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6334620714187622},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.608013927936554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834905505180359},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5272746682167053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4875625967979431},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4543461501598358},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41969162225723267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1363106667995453},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2459827252","display_name":null,"funder_award_id":"2018YFB1403202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3781173328","display_name":"\u9762\u5411\u89c6\u969c\u7528\u6237\u7684\u591a\u901a\u9053\u5a92\u4f53\u667a\u80fd\u8ba1\u7b97\u6280\u672f\u7814\u7a76","funder_award_id":"61972349","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W9770290","https://openalex.org/W1528802670","https://openalex.org/W1998808035","https://openalex.org/W2024550919","https://openalex.org/W2033365921","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2101498401","https://openalex.org/W2108598243","https://openalex.org/W2138204974","https://openalex.org/W2146444479","https://openalex.org/W2149350210","https://openalex.org/W2149557440","https://openalex.org/W2152790380","https://openalex.org/W2155855695","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2294130536","https://openalex.org/W2340690086","https://openalex.org/W2466618734","https://openalex.org/W2471768434","https://openalex.org/W2581017733","https://openalex.org/W2624614404","https://openalex.org/W2735001949","https://openalex.org/W2752782242","https://openalex.org/W2760103357","https://openalex.org/W2765440071","https://openalex.org/W2798951647","https://openalex.org/W2889167066","https://openalex.org/W2905544595","https://openalex.org/W2909133588","https://openalex.org/W2912123770","https://openalex.org/W2948085278","https://openalex.org/W2950739196","https://openalex.org/W2953271441","https://openalex.org/W2963091558","https://openalex.org/W2963176022","https://openalex.org/W2963373069","https://openalex.org/W2963389687","https://openalex.org/W2963420686","https://openalex.org/W2963800509","https://openalex.org/W2963997278","https://openalex.org/W2964067226","https://openalex.org/W2964138017","https://openalex.org/W2964211610","https://openalex.org/W2965809241","https://openalex.org/W2966683369","https://openalex.org/W2968549119","https://openalex.org/W2971155163","https://openalex.org/W2982223282","https://openalex.org/W2986670728","https://openalex.org/W2988159742","https://openalex.org/W3023371261","https://openalex.org/W3026458074","https://openalex.org/W3092962760","https://openalex.org/W3096034082","https://openalex.org/W3099206234","https://openalex.org/W3208624098","https://openalex.org/W4232613155"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Image":[0,101],"retrieval":[1,231],"with":[2,10],"text":[3,30,151],"feedback":[4,31],"is":[5],"an":[6],"emerging":[7],"research":[8,64],"topic":[9],"the":[11,39,58,68,73,84,93,138,150,160,164,168,182,186,198,202,206,222],"objective":[12],"of":[13,76,107,128,179],"integrating":[14],"inputs":[15],"from":[16,78,159,181],"multiple":[17],"modalities":[18,144,227],"as":[19],"queries.":[20],"In":[21],"this":[22,36,46,119],"paper,":[23],"queries":[24,91],"contain":[25],"a":[26,52,98,194],"reference":[27,161],"image":[28,37,59,162,166,183,208],"plus":[29],"that":[32,218],"describes":[33],"modifications":[34],"between":[35,90,126,141,149,193,225],"and":[38,60,87,92,112,153,163,185,201,228],"desired":[40,94,165,207],"image.":[41,95],"The":[42],"existing":[43],"work":[44],"for":[45],"task":[47],"mainly":[48],"focuses":[49],"on":[50,212],"designing":[51],"new":[53],"fusion":[54,86,187,199],"network":[55,200],"to":[56,67,117],"compose":[57],"text.":[61],"Still,":[62],"little":[63],"pays":[65],"attention":[66,108,133],"modality":[69,139,184,188,223],"gap":[70,120,140,224],"caused":[71],"by":[72,121,145,167,189],"inconsistent":[74],"distribution":[75],"features":[77,180],"different":[79,129,142,226],"modalities,":[80],"which":[81,105],"dramatically":[82],"influences":[83],"feature":[85],"similarity":[88],"learning":[89],"We":[96],"propose":[97],"Distribution-Aligned":[99],"Text-based":[100],"Retrieval":[102],"(DATIR)":[103],"model,":[104],"consists":[106],"mutual":[109,114,134,147,173,191],"information":[110,115,135,148,174,192],"maximization":[111,136],"hierarchical":[113,172],"maximization,":[116,175],"bridge":[118,221],"increasing":[122],"non-linear":[123],"statistic":[124],"dependencies":[125],"representations":[127,204],"modalities.":[130],"More":[131],"specifically,":[132],"narrows":[137],"input":[143],"maximizing":[146],"representation":[152,157,196],"its":[154],"semantically":[155],"consistent":[156],"captured":[158],"difference":[169],"transformer.":[170],"For":[171],"it":[176],"aligns":[177],"distributions":[178],"estimating":[190],"single-layer":[195],"in":[197,205],"multi-level":[203],"encoder.":[209],"Extensive":[210],"experiments":[211],"three":[213],"large-scale":[214],"benchmark":[215],"datasets":[216],"demonstrate":[217],"we":[219],"can":[220],"achieve":[229],"state-of-the-art":[230],"performance.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}