{"id":"https://openalex.org/W2900953995","doi":"https://doi.org/10.1109/tip.2018.2882225","title":"Bi-Directional Spatial-Semantic Attention Networks for Image-Text Matching","display_name":"Bi-Directional Spatial-Semantic Attention Networks for Image-Text Matching","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2900953995","doi":"https://doi.org/10.1109/tip.2018.2882225","mag":"2900953995","pmid":"https://pubmed.ncbi.nlm.nih.gov/30452372"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2882225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2882225","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5033233243","display_name":"Feiran Huang","orcid":"https://orcid.org/0000-0003-4294-0212"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Huang","raw_affiliation_strings":["Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4294-0212","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462591","display_name":"Xiaoming Zhang","orcid":"https://orcid.org/0000-0002-6662-4102"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Zhang","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6662-4102","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722638","display_name":"Zhonghua Zhao","orcid":"https://orcid.org/0000-0001-9625-1119"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghua Zhao","raw_affiliation_strings":["National Computer Emergency Technical Team/Coordination Center of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computer Emergency Technical Team/Coordination Center of China, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036786337","display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2022,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.96786379,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":"4","first_page":"2008","last_page":"2020"},"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":0.9991999864578247,"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":0.9965000152587891,"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":0.7649799585342407},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.7108651399612427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7013300657272339},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6098616123199463},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.598387598991394},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5519235134124756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5068870186805725},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48768532276153564},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4671693742275238},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4461308419704437},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.41680777072906494},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.365469753742218},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3353559672832489},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12072446942329407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1180543303489685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649799585342407},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7108651399612427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7013300657272339},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6098616123199463},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.598387598991394},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5519235134124756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5068870186805725},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48768532276153564},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4671693742275238},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4461308419704437},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41680777072906494},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.365469753742218},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3353559672832489},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12072446942329407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1180543303489685},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2018.2882225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2882225","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:30452372","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30452372","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2323930268","display_name":null,"funder_award_id":"U1636211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5152102630","display_name":null,"funder_award_id":"U1636210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5545615564","display_name":null,"funder_award_id":"4182037","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8321550385","display_name":null,"funder_award_id":"SKLSDE-2017ZX-19","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W21006490","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1523385540","https://openalex.org/W1527575280","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1836465849","https://openalex.org/W1853881680","https://openalex.org/W1861492603","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1928906481","https://openalex.org/W1931795219","https://openalex.org/W1949478088","https://openalex.org/W1988674770","https://openalex.org/W2014854862","https://openalex.org/W2031489346","https://openalex.org/W2070753207","https://openalex.org/W2100235303","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2130230179","https://openalex.org/W2133564696","https://openalex.org/W2142674578","https://openalex.org/W2150600350","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2340690086","https://openalex.org/W2463565445","https://openalex.org/W2474425175","https://openalex.org/W2476624367","https://openalex.org/W2530846021","https://openalex.org/W2538374209","https://openalex.org/W2546696630","https://openalex.org/W2555042572","https://openalex.org/W2560645892","https://openalex.org/W2574447816","https://openalex.org/W2604729005","https://openalex.org/W2751525844","https://openalex.org/W2765268259","https://openalex.org/W2807714591","https://openalex.org/W2949117887","https://openalex.org/W2949967295","https://openalex.org/W2953106684","https://openalex.org/W2962706528","https://openalex.org/W2963040148","https://openalex.org/W2963389687","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2963875806","https://openalex.org/W2963954913","https://openalex.org/W2964308564","https://openalex.org/W3037725825","https://openalex.org/W6600827882","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631216910","https://openalex.org/W6631516269","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/W6640376812","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6679434410","https://openalex.org/W6692004142","https://openalex.org/W6704508018","https://openalex.org/W6719057275","https://openalex.org/W6728094556","https://openalex.org/W6729399837","https://openalex.org/W6730549503","https://openalex.org/W6732292492","https://openalex.org/W6736419893"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2371905728","https://openalex.org/W2358103843"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,24,175,186],"by":[2],"deep":[3,82,155],"models":[4],"has":[5],"recently":[6],"made":[7],"remarkable":[8],"achievements":[9],"in":[10,30,79,142],"many":[11],"tasks,":[12],"such":[13],"as":[14,118],"image":[15,18,26,73,105,178],"caption":[16],"and":[17,27,40,72,179,198],"search.":[19],"A":[20],"major":[21],"challenge":[22],"of":[23,159,177,196],"the":[25,43,66,92,104,112,119,124,127,135,143,146,160,174,194],"text":[28,180],"lies":[29],"that":[31],"they":[32],"usually":[33],"have":[34],"complicated":[35],"underlying":[36],"relations":[37,44],"between":[38],"them":[39],"simply":[41],"modeling":[42],"may":[45],"lead":[46],"to":[47,68,75,89,102,111,133,149,172,183],"suboptimal":[48],"performance.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,95],"develop":[54],"a":[55,80,154,166],"novel":[56],"approach":[57,189],"Bi-directional":[58],"Spatial-Semantic":[59],"Attention":[60],"Networks":[61],"(BSSAN),":[62],"which":[63,107,115],"leverages":[64],"both":[65,158],"word":[67],"regions":[69,106],"(W2R)":[70],"relation":[71,78],"object":[74,141,148],"words":[76,137,150],"(O2W)":[77,151],"holistic":[81,167],"framework":[83,169],"for":[84,138],"more":[85,109],"effectively":[86,90],"matching.":[87],"Specifically,":[88],"encode":[91],"W2R":[93,120],"relation,":[94],"adopt":[96],"LSTM":[97],"with":[98],"bilinear":[99],"attention":[100,121,129,163],"function":[101],"infer":[103],"are":[108],"related":[110],"particular":[113],"words,":[114],"is":[116,131,170],"referred":[117],"network.":[122],"On":[123],"other":[125],"side,":[126],"O2W":[128],"network":[130],"proposed":[132,171],"discover":[134],"semanticallyclose":[136],"each":[139],"visual":[140,147],"image,":[144],"i.e.,":[145],"relation.":[152],"Then":[153],"model":[156],"unifying":[157],"two":[161],"directional":[162],"networks":[164],"into":[165],"learning":[168],"learn":[173],"scores":[176],"pairs.":[181],"Compared":[182],"existing":[184],"image-text":[185],"methods,":[187],"our":[188],"achieves":[190],"state-of-the-art":[191],"performance":[192],"on":[193],"datasets":[195],"Flickr30K":[197],"MSCOCO.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}