{"id":"https://openalex.org/W2982223282","doi":"https://doi.org/10.1145/3343031.3351053","title":"Learning Disentangled Representation for Cross-Modal Retrieval with Deep Mutual Information Estimation","display_name":"Learning Disentangled Representation for Cross-Modal Retrieval with Deep Mutual Information Estimation","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982223282","doi":"https://doi.org/10.1145/3343031.3351053","mag":"2982223282"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5048432022","display_name":"Weikuo Guo","orcid":"https://orcid.org/0000-0003-2830-3962"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weikuo Guo","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005195235","display_name":"Huaibo Huang","orcid":"https://orcid.org/0000-0001-5866-2283"},"institutions":[{"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"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaibo Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences & CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003239155","display_name":"Xiangwei Kong","orcid":"https://orcid.org/0000-0002-0851-6752"},"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":"Xiangwei Kong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"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"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["University of Chinese Academy of Sciences & CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048432022"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":1.5184,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.8658819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1712","last_page":"1720"},"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":0.9950000047683716,"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/interpretability","display_name":"Interpretability","score":0.791866660118103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7488481998443604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6596017479896545},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6387056708335876},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5729570388793945},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5542369484901428},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5373164415359497},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5228079557418823},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5122934579849243},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5107002854347229},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5084244608879089},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47947439551353455},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46098241209983826},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4606779217720032},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.46001455187797546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4048888385295868},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3596538007259369}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.791866660118103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488481998443604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6596017479896545},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6387056708335876},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5729570388793945},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5542369484901428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5373164415359497},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5228079557418823},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5122934579849243},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5107002854347229},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5084244608879089},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47947439551353455},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46098241209983826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4606779217720032},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.46001455187797546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4048888385295868},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3596538007259369},{"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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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":46,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2108384452","https://openalex.org/W2122925692","https://openalex.org/W2136144249","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2266728343","https://openalex.org/W2434741482","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2575842049","https://openalex.org/W2605135824","https://openalex.org/W2606473278","https://openalex.org/W2737047298","https://openalex.org/W2753738274","https://openalex.org/W2759194679","https://openalex.org/W2765440071","https://openalex.org/W2778940641","https://openalex.org/W2785519580","https://openalex.org/W2791006446","https://openalex.org/W2798813225","https://openalex.org/W2801365175","https://openalex.org/W2803398058","https://openalex.org/W2803832867","https://openalex.org/W2896822580","https://openalex.org/W2897135094","https://openalex.org/W2897457738","https://openalex.org/W2918552355","https://openalex.org/W2944906272","https://openalex.org/W2951873722","https://openalex.org/W2962777029","https://openalex.org/W2962823158","https://openalex.org/W2963224792","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963826681","https://openalex.org/W2963899908","https://openalex.org/W2964121744","https://openalex.org/W3159890710","https://openalex.org/W4232613155"],"related_works":["https://openalex.org/W2101924850","https://openalex.org/W2188315358","https://openalex.org/W4387724891","https://openalex.org/W2137853824","https://openalex.org/W2530029028","https://openalex.org/W2594350003","https://openalex.org/W2136482299","https://openalex.org/W31749436","https://openalex.org/W2337819340","https://openalex.org/W2070118902"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,139],"has":[2],"become":[3],"a":[4,20,42],"hot":[5],"research":[6],"topic":[7],"in":[8],"recent":[9],"years":[10],"for":[11,23,35],"its":[12,72],"theoretical":[13],"and":[14,33,71,135],"practical":[15],"significance.":[16],"This":[17,95],"paper":[18],"proposes":[19],"new":[21],"technique":[22],"learning":[24],"such":[25],"deep":[26,53],"visual-semantic":[27,133],"embedding":[28,134],"that":[29,127],"is":[30,57,81],"more":[31],"effective":[32],"interpretable":[34],"cross-modal":[36,138],"retrieval.":[37],"The":[38],"proposed":[39],"method":[40,129],"employs":[41],"two-stage":[43],"strategy":[44],"to":[45,62,83,86,97,104],"fulfill":[46],"the":[47,50,60,64,68,75,84,88,92,99,105,113,116],"task.":[48],"In":[49,74],"first":[51],"stage,":[52,77],"mutual":[54,65],"information":[55,66,90,103],"estimation":[56],"incorporated":[58],"into":[59],"objective":[61],"maximize":[63],"between":[67],"input":[69],"data":[70],"embedding.":[73],"second":[76],"an":[78],"expelling":[79],"branch":[80],"added":[82],"network":[85],"disentangle":[87],"modality-exclusive":[89,102],"from":[91],"learned":[93,117],"representations.":[94],"helps":[96],"reduce":[98],"impact":[100],"of":[101,115],"common":[106],"subspace":[107],"representation":[108],"as":[109,111],"well":[110],"improve":[112],"interpretability":[114],"feature.":[118],"Extensive":[119],"experiments":[120],"on":[121],"two":[122],"large-scale":[123],"benchmark":[124],"datasets":[125],"demonstrate":[126],"our":[128],"can":[130],"learn":[131],"better":[132],"achieve":[136],"state-of-the-art":[137],"results.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}