{"id":"https://openalex.org/W2920485199","doi":"https://doi.org/10.1145/3297156.3297244","title":"Image-Text Embedding with Hierarchical Knowledge for Cross-Modal Retrieval","display_name":"Image-Text Embedding with Hierarchical Knowledge for Cross-Modal Retrieval","publication_year":2018,"publication_date":"2018-12-08","ids":{"openalex":"https://openalex.org/W2920485199","doi":"https://doi.org/10.1145/3297156.3297244","mag":"2920485199"},"language":"en","primary_location":{"id":"doi:10.1145/3297156.3297244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297244","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","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/A5102997534","display_name":"Sanghyun Seo","orcid":"https://orcid.org/0000-0002-9340-5861"},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sanghyun Seo","raw_affiliation_strings":["Dongguk University, Jung-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Dongguk University, Jung-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710223","display_name":"Juntae Kim","orcid":"https://orcid.org/0000-0003-3344-4591"},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juntae Kim","raw_affiliation_strings":["Dongguk University, Jung-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Dongguk University, Jung-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I205490536"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102997534"],"corresponding_institution_ids":["https://openalex.org/I205490536"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24484339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"353"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8840477466583252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6343464851379395},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6166003942489624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5896639823913574},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.5802449584007263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48009994626045227},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47493842244148254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4708012342453003},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.44665783643722534},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41751474142074585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27679380774497986},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06880119442939758}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8840477466583252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6343464851379395},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6166003942489624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5896639823913574},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.5802449584007263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48009994626045227},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47493842244148254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4708012342453003},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.44665783643722534},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41751474142074585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27679380774497986},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06880119442939758},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297156.3297244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297156.3297244","pdf_url":null,"source":{"id":"https://openalex.org/S4306523626","display_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7617684519","display_name":null,"funder_award_id":"NRF-2017M3C4A7083279","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W14027548","https://openalex.org/W1686810756","https://openalex.org/W2062797058","https://openalex.org/W2106053110","https://openalex.org/W2123024445","https://openalex.org/W2250539671","https://openalex.org/W2963389687","https://openalex.org/W2963775347","https://openalex.org/W3091905774","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W2013985456","https://openalex.org/W2951564084","https://openalex.org/W4302984940","https://openalex.org/W2776807270","https://openalex.org/W2392685819","https://openalex.org/W2901841427"],"abstract_inverted_index":{"Heterogeneous":[0],"data":[1,11,29,128],"embedding":[2,22,47,70,146,167],"is":[3,83,129],"a":[4,13,18,36,96,132],"process":[5],"of":[6,10,17,58,68,110,138],"mapping":[7,25],"different":[8,33],"kinds":[9],"into":[12,35,131],"common":[14,37,133],"vector":[15,38,134],"space":[16],"certain":[19],"dimension.":[20],"Image-text":[21],"also":[23],"means":[24],"image":[26],"and":[27,55,158],"text":[28,59],"that":[30,104,125,145,159],"have":[31,115],"completely":[32],"characteristics":[34],"space.":[39],"In":[40,78],"this":[41],"paper,":[42],"we":[43],"propose":[44],"an":[45],"image-text":[46],"method":[48,63],"using":[49,154],"hierarchical":[50,97,148],"knowledge":[51,149],"such":[52],"as":[53],"coarse":[54,75,101,117],"fine":[56,93,112],"labels":[57,94,113],"data.":[60],"The":[61],"proposed":[62,156],"improves":[64],"the":[65,69,74,80,88,92,100,105,108,111,123,136,155],"training":[66],"efficiency":[67],"model":[71],"by":[72,85],"fixing":[73],"label":[76,118],"vectors.":[77],"addition,":[79],"loss":[81],"function":[82],"designed":[84],"arbitrarily":[86],"selecting":[87],"negative":[89],"sample":[90],"from":[91],"having":[95],"relationship":[98],"with":[99,147],"label,":[102],"so":[103],"difference":[106],"between":[107],"vectors":[109],"which":[114],"same":[116],"becomes":[119,140],"larger.":[120],"So,":[121],"when":[122],"images":[124,139],"are":[126],"visual":[127],"mapped":[130],"space,":[135],"semantic":[137],"clear.":[141],"Experimental":[142],"results":[143],"show":[144],"has":[150],"been":[151],"successfully":[152],"performed":[153,165],"methodology":[157],"cross-modal":[160],"retrieval":[161],"can":[162],"be":[163],"efficiently":[164],"through":[166],"model.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}