{"id":"https://openalex.org/W3159088493","doi":"https://doi.org/10.1145/3412847","title":"HCMSL: Hybrid Cross-modal Similarity Learning for Cross-modal Retrieval","display_name":"HCMSL: Hybrid Cross-modal Similarity Learning for Cross-modal Retrieval","publication_year":2021,"publication_date":"2021-01-31","ids":{"openalex":"https://openalex.org/W3159088493","doi":"https://doi.org/10.1145/3412847","mag":"3159088493"},"language":"en","primary_location":{"id":"doi:10.1145/3412847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412847","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101955004","display_name":"Chengyuan Zhang","orcid":"https://orcid.org/0000-0003-2721-6867"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengyuan Zhang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866910","display_name":"Jiayu Song","orcid":"https://orcid.org/0000-0003-4741-3876"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Song","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037340898","display_name":"Xiaofeng Zhu","orcid":"https://orcid.org/0000-0001-6840-0578"},"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":"Xiaofeng Zhu","raw_affiliation_strings":["School of Computer Science and Engineering at University of Electronic Science and Technology of China, Chengdu, Sichuan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering at University of Electronic Science and Technology of China, Chengdu, Sichuan","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394072","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-1685-7968"},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]},{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["College of Information and Intelligence, Hunan Agricultural University School of Computer Science and Engineering, Central South University"],"affiliations":[{"raw_affiliation_string":"College of Information and Intelligence, Hunan Agricultural University School of Computer Science and Engineering, Central South University","institution_ids":["https://openalex.org/I139660479","https://openalex.org/I52180223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100764178","display_name":"Shichao Zhang","orcid":"https://orcid.org/0000-0001-9981-2970"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101955004"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":4.651,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95992026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"17","issue":"1s","first_page":"1","last_page":"22"},"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":0.998199999332428,"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":0.984000027179718,"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/modal","display_name":"Modal","score":0.8932603597640991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998620271682739},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.642055332660675},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6183058619499207},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5878222584724426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5741424560546875},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5403422117233276},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5047260522842407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4433925747871399},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34504324197769165}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8932603597640991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998620271682739},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.642055332660675},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6183058619499207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5878222584724426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5741424560546875},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5403422117233276},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5047260522842407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4433925747871399},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34504324197769165},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3412847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412847","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7188871089","display_name":null,"funder_award_id":"61702560, 62072166, 61836016, and 61672177","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1489116628","https://openalex.org/W1832693441","https://openalex.org/W1964073652","https://openalex.org/W1976258951","https://openalex.org/W1988423806","https://openalex.org/W2001313406","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2015175493","https://openalex.org/W2020842694","https://openalex.org/W2025341678","https://openalex.org/W2085375449","https://openalex.org/W2086958058","https://openalex.org/W2092103303","https://openalex.org/W2106277773","https://openalex.org/W2115752676","https://openalex.org/W2122110645","https://openalex.org/W2135128992","https://openalex.org/W2138118304","https://openalex.org/W2192994569","https://openalex.org/W2210322478","https://openalex.org/W2243225650","https://openalex.org/W2294493913","https://openalex.org/W2326180695","https://openalex.org/W2519432244","https://openalex.org/W2523684233","https://openalex.org/W2526152041","https://openalex.org/W2582558662","https://openalex.org/W2605362976","https://openalex.org/W2605649771","https://openalex.org/W2752197020","https://openalex.org/W2759194679","https://openalex.org/W2765440071","https://openalex.org/W2795832645","https://openalex.org/W2799150641","https://openalex.org/W2807985910","https://openalex.org/W2887057599","https://openalex.org/W2889024947","https://openalex.org/W2926636120","https://openalex.org/W2951748488","https://openalex.org/W2962805368","https://openalex.org/W2962835968","https://openalex.org/W2964130424","https://openalex.org/W2964430790","https://openalex.org/W2967957126","https://openalex.org/W2970427386","https://openalex.org/W2981352610","https://openalex.org/W2994069755","https://openalex.org/W2997298113","https://openalex.org/W2998641113","https://openalex.org/W3005234306","https://openalex.org/W3014509175","https://openalex.org/W3022797367","https://openalex.org/W3105204788"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2364594919","https://openalex.org/W2167092671","https://openalex.org/W2385859805","https://openalex.org/W1861706286","https://openalex.org/W2530972254","https://openalex.org/W2219338811","https://openalex.org/W2149583853","https://openalex.org/W2143002539","https://openalex.org/W627697492"],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,32,46,123,142],"cross-modal":[3,47,65,89,109,127,162],"retrieval":[4,48,66,163],"is":[5,49,118],"to":[6,15,51,79,107,125,136],"find":[7],"the":[8,30,43,53,160],"relationship":[9],"between":[10,55,120],"different":[11,33,56],"modal":[12,18,27],"samples":[13,19,141],"and":[14,39,87,91],"retrieve":[16],"other":[17],"with":[20,94],"similar":[21],"semantics":[22],"by":[23],"using":[24],"a":[25,63,99,113],"certain":[26],"sample.":[28],"As":[29],"data":[31],"modalities":[34],"presents":[35],"heterogeneous":[36],"low-level":[37],"feature":[38,110],"semantic-related":[40],"high-level":[41],"features,":[42],"main":[44],"problem":[45],"how":[50],"measure":[52],"similarity":[54,139],"modalities.":[57],"In":[58],"this":[59],"article,":[60],"we":[61],"present":[62],"novel":[64],"method,":[67],"named":[68],"Hybrid":[69],"Cross-Modal":[70],"Similarity":[71],"Learning":[72],"model":[73],"(HCMSL":[74],"for":[75],"short).":[76],"It":[77],"aims":[78],"capture":[80],"sufficient":[81],"semantic":[82],"information":[83],"from":[84,140],"both":[85],"labeled":[86],"unlabeled":[88],"pairs":[90,93],"intra-modal":[92,138],"same":[95,143],"classification":[96],"label.":[97],"Specifically,":[98],"coupled":[100],"deep":[101],"fully":[102],"connected":[103],"networks":[104,124],"are":[105,134],"used":[106],"map":[108],"representations":[111],"into":[112],"common":[114],"subspace.":[115],"Weight-sharing":[116],"strategy":[117],"utilized":[119],"two":[121,130],"branches":[122],"diminish":[126],"heterogeneity.":[128],"Furthermore,":[129],"Siamese":[131],"CNN":[132],"models":[133],"employed":[135],"learn":[137],"modality.":[144],"Comprehensive":[145],"experiments":[146],"on":[147],"real":[148],"datasets":[149],"clearly":[150],"demonstrate":[151],"that":[152],"our":[153],"proposed":[154],"technique":[155],"achieves":[156],"substantial":[157],"improvements":[158],"over":[159],"state-of-the-art":[161],"techniques.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}