{"id":"https://openalex.org/W2982078236","doi":"https://doi.org/10.1145/3343031.3350869","title":"Focus Your Attention","display_name":"Focus Your Attention","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982078236","doi":"https://doi.org/10.1145/3343031.3350869","mag":"2982078236"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350869","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/A5100386372","display_name":"Chunxiao Liu","orcid":"https://orcid.org/0000-0002-3307-9558"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Chunxiao Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059575276","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-4748-6426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Xiaomi AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100386372"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":8.6853,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.98213862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"11"},"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9781000018119812,"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/computer-science","display_name":"Computer science","score":0.7805940508842468},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7377399802207947},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7247477769851685},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.6977143287658691},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5927284955978394},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5536229014396667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5276780724525452},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5063961744308472},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.483989953994751},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.47975385189056396},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.45803263783454895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45732370018959045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08983781933784485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07541236281394958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805940508842468},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7377399802207947},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7247477769851685},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.6977143287658691},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5927284955978394},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5536229014396667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5276780724525452},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5063961744308472},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.483989953994751},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.47975385189056396},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.45803263783454895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45732370018959045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08983781933784485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07541236281394958},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350869","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":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W2112912048","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2606473278","https://openalex.org/W2619383789","https://openalex.org/W2732016772","https://openalex.org/W2739759426","https://openalex.org/W2745461083","https://openalex.org/W2778940641","https://openalex.org/W2894786240","https://openalex.org/W2900953995","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963091558","https://openalex.org/W2963954913","https://openalex.org/W2963966654","https://openalex.org/W2964120214"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2374013449","https://openalex.org/W2358990940","https://openalex.org/W73545470","https://openalex.org/W2093931120","https://openalex.org/W2364381299","https://openalex.org/W3196281958"],"abstract_inverted_index":{"Learning":[0],"semantic":[1,13,44,64,93],"correspondence":[2],"between":[3,15],"image":[4,31],"and":[5,17,26,32,88,180,193,227],"text":[6,56,203],"is":[7,22,141,164,187],"significant":[8],"as":[9,45],"it":[10],"bridges":[11],"the":[12,42,51,62,77,96,125,158,184],"gap":[14],"vision":[16],"language.":[18],"The":[19,135,161],"key":[20],"challenge":[21],"to":[23,61,76,92,116,118,131,198,201],"accurately":[24],"find":[25],"correlate":[27],"shared":[28,43,63,78,159],"semantics":[29],"in":[30,95,190],"text.":[33],"Most":[34],"existing":[35,139],"methods":[36],"achieve":[37],"this":[38,101],"goal":[39],"by":[40,166],"representing":[41],"a":[46,105],"weighted":[47],"combination":[48],"of":[49,222],"all":[50,124],"fragments":[52,59,120,130,156,175],"(image":[53],"regions":[54],"or":[55,84,204],"words),":[57],"where":[58],"relevant":[60,72,119,129,174],"obtain":[65],"more":[66,75,83],"attention,":[67],"otherwise":[68],"less.":[69],"However,":[70],"despite":[71],"ones":[73,81],"contribute":[74],"semantic,":[79],"irrelevant":[80,155],"will":[82,90],"less":[85],"disturb":[86],"it,":[87],"thus":[89],"lead":[91],"misalignment":[94],"correlation":[97],"phase.":[98],"To":[99],"address":[100],"issue,":[102],"we":[103],"present":[104],"novel":[106],"Bidirectional":[107],"Focal":[108],"Attention":[109],"Network":[110],"(BFAN),":[111],"which":[112,196],"not":[113],"only":[114],"allows":[115],"attend":[117],"but":[121,211],"also":[122],"diverts":[123],"attention":[126,147,163,168,186],"into":[127],"these":[128],"concentrate":[132],"on":[133,145,153,170,177,224],"them.":[134],"main":[136],"difference":[137],"with":[138,217],"works":[140],"they":[142],"mostly":[143],"focus":[144,152],"learning":[146],"weight":[148],"while":[149],"our":[150,209],"BFAN":[151],"eliminating":[154],"from":[157],"semantic.":[160],"focal":[162,185],"achieved":[165],"preassigning":[167],"based":[169,176],"inter-modality":[171],"relation,":[172],"identifying":[173],"intra-modality":[178],"relation":[179],"reassigning":[181],"attention.":[182],"Furthermore,":[183],"jointly":[188],"applied":[189],"both":[191,225],"image-to-text":[192],"text-to-image":[194],"directions,":[195],"enables":[197],"avoid":[199],"preference":[200],"long":[202],"complex":[205],"image.":[206],"Experiments":[207],"show":[208],"simple":[210],"effective":[212],"framework":[213],"significantly":[214],"outperforms":[215],"state-of-the-art,":[216],"relative":[218],"[email":[219],"protected]":[220],"gains":[221],"2.2%":[223],"Flicr30K":[226],"MSCOCO":[228],"benchmarks.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}