{"id":"https://openalex.org/W2987222078","doi":"https://doi.org/10.1145/3357384.3358104","title":"Cross-modal Image-Text Retrieval with Multitask Learning","display_name":"Cross-modal Image-Text Retrieval with Multitask Learning","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2987222078","doi":"https://doi.org/10.1145/3357384.3358104","mag":"2987222078"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358104","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 Information and Knowledge Management","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/A5101912906","display_name":"Junyu Luo","orcid":"https://orcid.org/0009-0001-6894-1144"},"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/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Luo","raw_affiliation_strings":["SIAT, Chinese Academy of Sciences & Sichuan University, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIAT, Chinese Academy of Sciences & Sichuan University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074799043","display_name":"Ying Shen","orcid":"https://orcid.org/0000-0002-3220-904X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shen","raw_affiliation_strings":["Peking University, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068007462","display_name":"Xiang Ao","orcid":"https://orcid.org/0000-0001-9633-8361"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Ao","raw_affiliation_strings":["ICT, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"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":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054067088","display_name":"Min Yang","orcid":"https://orcid.org/0000-0003-3814-2728"},"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/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["SIAT, Chinese Academy of Sciences, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIAT, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2309","last_page":"2312"},"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":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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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":0.7553900480270386},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7276865839958191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5983763337135315},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5245487689971924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48932215571403503},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4874441921710968},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.477680504322052},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.43196019530296326},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.42848584055900574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3883536458015442},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35629725456237793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11348128318786621}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553900480270386},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7276865839958191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5983763337135315},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5245487689971924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48932215571403503},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4874441921710968},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.477680504322052},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.43196019530296326},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.42848584055900574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3883536458015442},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35629725456237793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11348128318786621},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3358104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358104","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 Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W199018803","https://openalex.org/W1523385540","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1883346539","https://openalex.org/W1964073652","https://openalex.org/W1970055505","https://openalex.org/W2006031689","https://openalex.org/W2100235303","https://openalex.org/W2155803963","https://openalex.org/W2213253086","https://openalex.org/W2606473278","https://openalex.org/W2795832645","https://openalex.org/W2795852031","https://openalex.org/W2950220902"],"related_works":["https://openalex.org/W2134880816","https://openalex.org/W2111298487","https://openalex.org/W2765199869","https://openalex.org/W2055498716","https://openalex.org/W4386075138","https://openalex.org/W1984130439","https://openalex.org/W3016499519","https://openalex.org/W2371359060","https://openalex.org/W2562873141","https://openalex.org/W2510680828"],"abstract_inverted_index":{"In":[0,57],"this":[1],"paper,":[2],"we":[3,36],"propose":[4,37],"a":[5,14,38,100],"multi-task":[6],"learning":[7],"approach":[8],"for":[9,19,42],"cross-modal":[10,40,43,65,78,97],"image-text":[11],"retrieval.":[12],"First,":[13],"correlation":[15],"network":[16,104],"is":[17,90,105,138],"proposed":[18],"relation":[20],"recognition":[21],"task,":[22,46],"which":[23,47],"helps":[24,48],"learn":[25],"the":[26,50,62,77,82,109,131],"complicated":[27],"relations":[28],"and":[29,71,89,111],"common":[30,84],"information":[31,85],"of":[32,53,64],"different":[33],"modalities.":[34],"Then,":[35],"correspondence":[39],"autoencoder":[41],"input":[44],"reconstruction":[45],"correlate":[49],"hidden":[51],"representations":[52],"two":[54,67,120],"uni-modal":[55],"autoencoders.":[56],"addition,":[58],"to":[59,76,94,107],"further":[60],"improve":[61],"performance":[63],"retrieval,":[66],"regularization":[68],"terms":[69],"(variance":[70],"consistency":[72],"constraints)":[73],"are":[74],"introduced":[75],"embeddings":[79,113],"such":[80],"that":[81,124],"learned":[83],"has":[86,127],"large":[87],"variance":[88],"modality":[91],"invariant.":[92],"Finally,":[93],"enable":[95],"large-scale":[96],"similarity":[98],"search,":[99],"flexible":[101],"binary":[102,115],"transform":[103],"designed":[106],"convert":[108],"text":[110],"image":[112],"into":[114],"codes.":[116],"Extensive":[117],"experiments":[118],"on":[119],"benchmark":[121],"datasets":[122],"demonstrate":[123],"our":[125],"model":[126],"robust":[128],"superiority":[129],"over":[130],"compared":[132],"strong":[133],"baseline":[134],"methods.":[135],"Source":[136],"code":[137],"available":[139],"at":[140],"\\urlhttps://github.com/daerv/DAEVR.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}