{"id":"https://openalex.org/W2981586349","doi":"https://doi.org/10.1145/3343031.3350940","title":"Learning Fragment Self-Attention Embeddings for Image-Text Matching","display_name":"Learning Fragment Self-Attention Embeddings for Image-Text Matching","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981586349","doi":"https://doi.org/10.1145/3343031.3350940","mag":"2981586349"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350940","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/A5101973798","display_name":"Yiling Wu","orcid":"https://orcid.org/0000-0002-7598-7183"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiling Wu","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008752777","display_name":"Guoli Song","orcid":"https://orcid.org/0000-0002-5452-3697"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoli Song","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101973798"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":6.0733,"has_fulltext":false,"cited_by_count":126,"citation_normalized_percentile":{"value":0.97092838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2088","last_page":"2096"},"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":0.9944000244140625,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9923999905586243,"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":0.8117904663085938},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.6861299872398376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6506897211074829},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.573674201965332},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5579638481140137},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5426200032234192},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5318350791931152},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5250387191772461},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5050433278083801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4915841519832611},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45702454447746277},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.43239128589630127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1254328489303589},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11722418665885925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1051253080368042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117904663085938},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.6861299872398376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6506897211074829},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.573674201965332},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5579638481140137},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5426200032234192},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5318350791931152},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5250387191772461},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5050433278083801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4915841519832611},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45702454447746277},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43239128589630127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1254328489303589},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11722418665885925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1051253080368042},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350940","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":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1949478088","https://openalex.org/W2025341678","https://openalex.org/W2070753207","https://openalex.org/W2071207147","https://openalex.org/W2153579005","https://openalex.org/W2155258183","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2210322478","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2316082076","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2555897561","https://openalex.org/W2562607067","https://openalex.org/W2623201052","https://openalex.org/W2739759426","https://openalex.org/W2745461083","https://openalex.org/W2884585870","https://openalex.org/W2894786240","https://openalex.org/W2933775054","https://openalex.org/W2953106684","https://openalex.org/W2962964995","https://openalex.org/W2963091558","https://openalex.org/W2963389687","https://openalex.org/W2963403868","https://openalex.org/W2963536419","https://openalex.org/W2963882743","https://openalex.org/W2963988212","https://openalex.org/W2964081303","https://openalex.org/W2964120214","https://openalex.org/W6600109629"],"related_works":["https://openalex.org/W1973480752","https://openalex.org/W4253208712","https://openalex.org/W3132641048","https://openalex.org/W1603677234","https://openalex.org/W2217679042","https://openalex.org/W2525971763","https://openalex.org/W2805502594","https://openalex.org/W2783178962","https://openalex.org/W1896179566","https://openalex.org/W2984753899"],"abstract_inverted_index":{"In":[0,69],"image-text":[1,198],"matching":[2,8,199],"task,":[3],"the":[4,13,29,143,149,154,173],"key":[5],"to":[6,11,45,47,77,119],"good":[7],"quality":[9],"is":[10],"capture":[12,165],"rich":[14],"contextual":[15],"dependencies":[16],"between":[17,62],"fragments":[18],"of":[19,31,35,133],"image":[20,36,48,64,101,127],"and":[21,38,50,66,88,94,107,122,128,137,152,164,180,193,195,201,206],"text.":[22],"However,":[23],"previous":[24],"works":[25],"either":[26],"simply":[27],"aggregate":[28,89],"similarity":[30,60],"all":[32,63],"possible":[33],"pairs":[34],"regions":[37,49,102,157],"words,":[39],"or":[40,83,160],"take":[41],"multi-step":[42],"cross":[43],"attention":[44],"attend":[46],"words":[51,161],"with":[52],"each":[53],"other":[54],"as":[55,111],"context,":[56],"which":[57,131],"requires":[58],"exhaustive":[59],"computation":[61],"region":[65],"word":[67],"pairs.":[68],"this":[70],"paper,":[71],"we":[72],"propose":[73],"Self-Attention":[74],"Embeddings":[75],"(SAEM)":[76],"exploit":[78],"fragment":[79,90,124,144,150,175],"relations":[80,151],"in":[81,126,158,162,177],"images":[82,159,192],"texts":[84],"by":[85],"self-attention":[86,115,135,145],"mechanism,":[87],"information":[91],"into":[92],"visual":[93,179],"textual":[95,181],"embeddings.":[96],"Specifically,":[97],"SAEM":[98],"extracts":[99],"salient":[100,156],"based":[103],"on":[104,204],"bottom-up":[105],"attention,":[106],"takes":[108],"WordPiece":[109],"tokens":[110],"sentence":[112],"fragments.":[113],"The":[114],"layers":[116],"are":[117],"built":[118],"model":[120],"subtle":[121],"fine-grained":[123,174],"relation":[125,176],"text":[129],"respectively,":[130],"consists":[132],"multi-head":[134],"sub-layer":[136],"position-wise":[138],"feed-forward":[139],"network":[140],"sub-layer.":[141],"Consequently,":[142],"mechanism":[146],"can":[147],"discover":[148],"identify":[153],"semantically":[155,187],"sentences,":[163],"their":[166],"interaction":[167],"more":[168,186],"accurately.":[169],"By":[170],"simultaneously":[171],"exploiting":[172],"both":[178],"modalities,":[182],"our":[183],"method":[184],"produces":[185],"consistent":[188],"embeddings":[189],"for":[190],"representing":[191],"texts,":[194],"demonstrates":[196],"promising":[197],"accuracy":[200],"high":[202],"efficiency":[203],"Flickr30K":[205],"MSCOCO":[207],"datasets.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}