{"id":"https://openalex.org/W3009971095","doi":"https://doi.org/10.1109/wacv45572.2020.9093548","title":"MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding","display_name":"MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009971095","doi":"https://doi.org/10.1109/wacv45572.2020.9093548","mag":"3009971095"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5003397706","display_name":"Geondo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geondo Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017549954","display_name":"Chihye Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chihye Han","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103221173","display_name":"Dae\u2010Shik Kim","orcid":"https://orcid.org/0000-0002-9131-8086"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeshik Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081523374","display_name":"Wonjun Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103693","display_name":"Lutron Electronics (United States)","ror":"https://ror.org/01e55bn36","country_code":"US","type":"company","lineage":["https://openalex.org/I4210103693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonjun Yoon","raw_affiliation_strings":["Lunit Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lunit Inc","institution_ids":["https://openalex.org/I4210103693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1507","last_page":"1515"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8181455731391907},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7125779986381531},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6419446468353271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510382354259491},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4719732701778412},{"id":"https://openalex.org/keywords/visual-space","display_name":"Visual space","score":0.45675310492515564},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4446893632411957},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4388892352581024},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.4351482391357422},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.42437633872032166},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.42270779609680176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4176673889160156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3962233066558838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181455731391907},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7125779986381531},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6419446468353271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510382354259491},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4719732701778412},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.45675310492515564},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4446893632411957},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4388892352581024},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.4351482391357422},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.42437633872032166},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.42270779609680176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4176673889160156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3962233066558838},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1527575280","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2133564696","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2209647458","https://openalex.org/W2415204069","https://openalex.org/W2546696630","https://openalex.org/W2597655663","https://openalex.org/W2606473278","https://openalex.org/W2739181657","https://openalex.org/W2768454054","https://openalex.org/W2798782720","https://openalex.org/W2884585870","https://openalex.org/W2938728617","https://openalex.org/W2940929270","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963174729","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963467339","https://openalex.org/W2963843116","https://openalex.org/W2964120214","https://openalex.org/W2964276596","https://openalex.org/W2964308564","https://openalex.org/W4297810817","https://openalex.org/W4299801216","https://openalex.org/W4385245566","https://openalex.org/W6629028937","https://openalex.org/W6631516269","https://openalex.org/W6639102338","https://openalex.org/W6679434410","https://openalex.org/W6685183736","https://openalex.org/W6688086495","https://openalex.org/W6715743342","https://openalex.org/W6724699187","https://openalex.org/W6735377749","https://openalex.org/W6736658009","https://openalex.org/W6739901393","https://openalex.org/W6741383107","https://openalex.org/W6745654871","https://openalex.org/W6746466138","https://openalex.org/W6753038380","https://openalex.org/W6762066681"],"related_works":["https://openalex.org/W3140002740","https://openalex.org/W4226361842","https://openalex.org/W2255924030","https://openalex.org/W4210441873","https://openalex.org/W4205247775","https://openalex.org/W3156761522","https://openalex.org/W4292546934","https://openalex.org/W3034658947","https://openalex.org/W2980960567","https://openalex.org/W4285603042"],"abstract_inverted_index":{"Visual-semantic":[0],"embedding":[1,20,85],"enables":[2],"various":[3,96],"tasks":[4,120],"such":[5],"as":[6],"image-text":[7,118],"retrieval,":[8],"image":[9,76,143],"captioning,":[10],"and":[11,25,46,100,123,144,155],"visual":[12,24,45,99],"question":[13],"answering.":[14],"The":[15],"key":[16],"to":[17,22,82,94,105],"successful":[18],"visual-semantic":[19,157],"is":[21],"express":[23],"textual":[26,47,101],"data":[27,48,62,102],"properly":[28],"by":[29,42,63,103],"accounting":[30],"for":[31],"their":[32],"intricate":[33],"relationship.":[34],"While":[35],"previous":[36],"studies":[37],"have":[38],"achieved":[39],"much":[40],"advance":[41],"encoding":[43],"the":[44,68,83,113,127,130,142,145],"into":[49],"a":[50,64,89],"joint":[51,84,158],"space":[52],"where":[53],"similar":[54],"concepts":[55],"are":[56],"closely":[57],"located,":[58],"they":[59],"often":[60],"represent":[61],"single":[65],"vector":[66],"ignoring":[67],"presence":[69],"of":[70,98,129],"multiple":[71,139],"important":[72,106],"components":[73,97,137],"in":[74,80,108,117,141],"an":[75,153],"or":[77],"text.":[78],"Thus,":[79],"addition":[81],"space,":[86],"we":[87,147],"propose":[88],"novel":[90],"multi-head":[91],"self-attention":[92],"network":[93],"capture":[95,134],"attending":[104],"parts":[107],"data.":[109],"Our":[110],"approach":[111],"achieves":[112,152],"new":[114],"state-of-the-art":[115],"results":[116],"retrieval":[119],"on":[121],"MS-COCO":[122],"Flicker30K":[124],"datasets.":[125],"Through":[126],"visualization":[128],"attention":[131],"maps":[132],"that":[133,149],"distinct":[135],"semantic":[136],"at":[138],"positions":[140],"text,":[146],"demonstrate":[148],"our":[150],"method":[151],"effective":[154],"interpretable":[156],"space.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}