{"id":"https://openalex.org/W2943911770","doi":"https://doi.org/10.1109/tcsvt.2019.2916167","title":"Matching Image and Sentence with Multi-faceted Representations","display_name":"Matching Image and Sentence with Multi-faceted Representations","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2943911770","doi":"https://doi.org/10.1109/tcsvt.2019.2916167","mag":"2943911770"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2019.2916167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2916167","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Tencent AI Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024453719","display_name":"Wenhao Jiang","orcid":"https://orcid.org/0000-0002-0795-366X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Jiang","raw_affiliation_strings":["Tencent AI Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Tencent AI Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Jilian Technology Group (Video++), Shanghai, China","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilian Technology Group (Video++), Shanghai, China","institution_ids":["https://openalex.org/I4210099297"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Tencent AI Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0843,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89951881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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":0.9897000193595886,"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/sentence","display_name":"Sentence","score":0.8638176918029785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437680959701538},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6757031679153442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6226137280464172},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5865408778190613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5294864773750305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5123380422592163},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4981248378753662},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49340763688087463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14221176505088806}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8638176918029785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437680959701538},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6757031679153442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6226137280464172},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5865408778190613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5294864773750305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5123380422592163},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4981248378753662},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49340763688087463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14221176505088806},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2019.2916167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2916167","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W21006490","https://openalex.org/W68733909","https://openalex.org/W87822204","https://openalex.org/W92662927","https://openalex.org/W1486649854","https://openalex.org/W1527575280","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1836465849","https://openalex.org/W1853881680","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1904365287","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2062227835","https://openalex.org/W2069222105","https://openalex.org/W2096663965","https://openalex.org/W2105709960","https://openalex.org/W2109586012","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2142192571","https://openalex.org/W2149557440","https://openalex.org/W2151321368","https://openalex.org/W2159243025","https://openalex.org/W2169278871","https://openalex.org/W2170738476","https://openalex.org/W2171361956","https://openalex.org/W2185175083","https://openalex.org/W2218145876","https://openalex.org/W2274287116","https://openalex.org/W2284126738","https://openalex.org/W2293453011","https://openalex.org/W2326180695","https://openalex.org/W2337005149","https://openalex.org/W2337086876","https://openalex.org/W2339652278","https://openalex.org/W2552161745","https://openalex.org/W2552579943","https://openalex.org/W2752585553","https://openalex.org/W2778940641","https://openalex.org/W2792035262","https://openalex.org/W2798280084","https://openalex.org/W2891894830","https://openalex.org/W2894786240","https://openalex.org/W2951359136","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2963040148","https://openalex.org/W2963389687","https://openalex.org/W2963579811","https://openalex.org/W2963899908","https://openalex.org/W2963954913","https://openalex.org/W2964138017","https://openalex.org/W2964350391","https://openalex.org/W3098232083","https://openalex.org/W4299801216","https://openalex.org/W6600334730","https://openalex.org/W6600827882","https://openalex.org/W6629028937","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6638742206","https://openalex.org/W6638897936","https://openalex.org/W6639102338","https://openalex.org/W6675968127","https://openalex.org/W6676497082","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6683512859","https://openalex.org/W6685160515","https://openalex.org/W6685183736","https://openalex.org/W6694260854","https://openalex.org/W6697449767"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2375873920","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2312145515"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,55],"propose":[4,56],"a":[5],"novel":[6,58],"multimodal":[7],"matching":[8,119,125],"model":[9,126],"for":[10],"the":[11,23,41,46,63,75,84,99,103,114,123,129,137],"image":[12,24,47,70,100,116],"and":[13,48,71,102,117,140],"sentence":[14,26,49,72,104,118],"based":[15,51,73],"on":[16,52,74,136],"their":[17,53],"multiple":[18,34,77,93],"representations.":[19],"Each":[20],"representation":[21],"of":[22,33,36,113],"or":[25],"undergoes":[27],"an":[28],"independent":[29],"neural":[30,85],"network,":[31],"consisting":[32],"layers":[35],"nonlinear":[37],"mappings":[38],"to":[39,60,82,97],"yield":[40],"corresponding":[42],"embedding.":[43],"Besides":[44],"exploiting":[45],"relationship":[50,64],"embeddings,":[54,78],"one":[57],"loss":[59],"further":[61],"exploit":[62],"within":[65],"each":[66],"single":[67],"modality,":[68],"namely,":[69],"yielded":[76],"which":[79],"is":[80],"used":[81],"train":[83],"networks":[86],"simultaneously.":[87],"The":[88],"experimental":[89],"results":[90],"demonstrate":[91],"that":[92],"representations":[94],"can":[95],"help":[96],"capture":[98],"contents":[101],"semantic":[105],"meaning":[106],"more":[107],"precisely,":[108],"thus":[109],"making":[110],"comprehensive":[111],"exploitations":[112],"complicated":[115],"relationship.":[120],"More":[121],"concretely,":[122],"proposed":[124],"significantly":[127],"outperforms":[128],"state-of-the-art":[130],"approaches":[131],"in":[132],"bidirectional":[133],"image-sentence":[134],"retrieval":[135],"Flickr8K,":[138],"Flickr30K,":[139],"Microsoft":[141],"COCO":[142],"datasets.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}