{"id":"https://openalex.org/W3092962760","doi":"https://doi.org/10.1145/3394171.3413917","title":"Joint Attribute Manipulation and Modality Alignment Learning for Composing Text and Image to Image Retrieval","display_name":"Joint Attribute Manipulation and Modality Alignment Learning for Composing Text and Image to Image Retrieval","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092962760","doi":"https://doi.org/10.1145/3394171.3413917","mag":"3092962760"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5100406150","display_name":"Feifei Zhang","orcid":"https://orcid.org/0000-0002-8153-9977"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081346568","display_name":"Mingliang Xu","orcid":"https://orcid.org/0000-0002-6885-3451"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xu","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Changsheng Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3367","last_page":"3376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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":0.9979000091552734,"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":0.82269287109375},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6424657702445984},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.638379693031311},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5922995805740356},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5852615833282471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4993293285369873},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4944188594818115},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.487468957901001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4697314500808716},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4592466354370117},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40746164321899414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37184804677963257},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1436128318309784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82269287109375},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6424657702445984},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.638379693031311},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5922995805740356},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5852615833282471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993293285369873},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4944188594818115},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.487468957901001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4697314500808716},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4592466354370117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40746164321899414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37184804677963257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1436128318309784},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1948251820","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2070753207","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2464503653","https://openalex.org/W2606473278","https://openalex.org/W2620341577","https://openalex.org/W2735001949","https://openalex.org/W2736809457","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2798553619","https://openalex.org/W2799263800","https://openalex.org/W2889167066","https://openalex.org/W2905544595","https://openalex.org/W2912459656","https://openalex.org/W2945895945","https://openalex.org/W2948037078","https://openalex.org/W2948490177","https://openalex.org/W2955811986","https://openalex.org/W2956018683","https://openalex.org/W2962714319","https://openalex.org/W2962747232","https://openalex.org/W2962869524","https://openalex.org/W2962945761","https://openalex.org/W2963306805","https://openalex.org/W2963997278","https://openalex.org/W2964019233","https://openalex.org/W2964138017","https://openalex.org/W2964211610","https://openalex.org/W2967957126","https://openalex.org/W2971974407","https://openalex.org/W2975813532","https://openalex.org/W2979304729","https://openalex.org/W2981384185","https://openalex.org/W2981473723","https://openalex.org/W2981669886","https://openalex.org/W2982512683","https://openalex.org/W2982905682","https://openalex.org/W2983339877","https://openalex.org/W2986755220","https://openalex.org/W2987391422","https://openalex.org/W2988281744","https://openalex.org/W2988823324","https://openalex.org/W2989883423","https://openalex.org/W2991524597","https://openalex.org/W2994818707","https://openalex.org/W2998631105","https://openalex.org/W3004349648","https://openalex.org/W3034951775","https://openalex.org/W3035096461","https://openalex.org/W3035356601","https://openalex.org/W3101029400","https://openalex.org/W3101531717","https://openalex.org/W3102718214"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2071180033","https://openalex.org/W2036058638","https://openalex.org/W2528082075","https://openalex.org/W155590726"],"abstract_inverted_index":{"Cross-model":[0],"retrieval":[1,81,211],"has":[2],"attracted":[3],"much":[4],"attention":[5,158],"in":[6,38,145,178],"recent":[7],"years":[8],"due":[9],"to":[10,22,34,45,55,64,101,115,139,213],"its":[11],"wide":[12],"applications.":[13],"Conventional":[14],"approaches":[15],"usually":[16],"take":[17],"one":[18],"modality":[19,118,217],"as":[20],"query":[21,57,66,84,107,122,170],"retrieve":[23],"relevant":[24,54],"data":[25],"of":[26,105],"another":[27],"modality.":[28],"In":[29,134],"this":[30,135],"paper,":[31,136],"we":[32,137],"devote":[33],"an":[35,202],"emerging":[36],"task":[37,75],"cross-modal":[39,71,210],"retrieval,":[40,72],"Composing":[41],"Text":[42],"and":[43,113,123,160,172],"Image":[44,46],"Retrieval":[47],"(CTI-IR),":[48],"which":[49,164],"aims":[50],"at":[51],"retrieving":[52],"images":[53],"a":[56,146,179],"image":[58,85,108,171],"with":[59,69,141],"text":[60,175,191],"describing":[61],"desired":[62],"modifications":[63],"the":[65,73,80,83,90,94,106,111,117,121,131,150,156,169,173,190,195,208,230],"image.":[67],"Compared":[68],"conventional":[70,209],"new":[74],"is":[76,153,205],"particularly":[77],"useful":[78],"for":[79,182,220],"that":[82,229],"does":[86],"not":[87],"perfectly":[88],"match":[89],"user's":[91],"expectations.":[92],"Generally,":[93],"CTI-IR":[95],"involves":[96],"two":[97],"underlying":[98],"problems:":[99],"how":[100,114],"manipulate":[102],"visual":[103,196],"features":[104,197],"specified":[109],"by":[110],"text,":[112],"model":[116],"gap":[119],"between":[120],"target.":[124],"Most":[125],"previous":[126],"methods":[127],"focus":[128],"on":[129,155,224],"solving":[130],"second":[132],"problem.":[133],"aim":[138],"deal":[140],"both":[142],"problems":[143],"simultaneously":[144],"unified":[147],"model.":[148],"Specifically,":[149],"proposed":[151,231],"method":[152,232],"based":[154],"graph":[157,181,199],"network":[159],"adversarial":[161,203],"learning":[162,183],"network,":[163],"enjoys":[165],"several":[166],"merits.":[167],"First,":[168],"modification":[174],"are":[176,192],"constructed":[177],"relation":[180],"text-adaptive":[184],"representations.":[185],"Second,":[186],"semantic":[187],"contents":[188],"from":[189],"injected":[193],"into":[194,207],"through":[198],"attention.":[200],"Third,":[201],"loss":[204,212],"incorporated":[206],"learn":[214],"more":[215],"discriminative":[216],"invariant":[218],"representations":[219],"CTI-IR.":[221],"Extensive":[222],"experiments":[223],"three":[225],"benchmark":[226],"datasets":[227],"demonstrate":[228],"performs":[233],"favorably":[234],"against":[235],"state-of-the-art":[236],"methods.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}