{"id":"https://openalex.org/W3015982325","doi":"https://doi.org/10.1109/icassp40776.2020.9054758","title":"Exploring Entity-Level Spatial Relationships for Image-Text Matching","display_name":"Exploring Entity-Level Spatial Relationships for Image-Text Matching","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015982325","doi":"https://doi.org/10.1109/icassp40776.2020.9054758","mag":"3015982325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5012045868","display_name":"Yaxian Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaxian Xia","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108745013","display_name":"Lun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Huang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017052768","display_name":"Wenmin Wang","orcid":"https://orcid.org/0000-0003-2664-4413"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenmin Wang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064374603","display_name":"Xiao-Yong Wei","orcid":"https://orcid.org/0000-0002-5706-5177"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Yong Wei","raw_affiliation_strings":["Peng Cheng Laboratory"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332984","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-9765-4523"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012045868"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54602742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"4452","last_page":"4456"},"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":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9966999888420105,"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":0.7878650426864624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6468247771263123},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6040896773338318},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.594124972820282},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.58747398853302},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5824669003486633},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5639373660087585},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5615522265434265},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5510764122009277},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.5140668153762817},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.486451119184494},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46342432498931885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4595353603363037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4307571053504944},{"id":"https://openalex.org/keywords/spatial-relationship","display_name":"Spatial relationship","score":0.41151589155197144},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16634872555732727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10924527049064636},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08809003233909607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878650426864624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6468247771263123},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6040896773338318},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.594124972820282},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.58747398853302},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5824669003486633},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5639373660087585},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5615522265434265},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5510764122009277},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5140668153762817},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.486451119184494},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46342432498931885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4595353603363037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4307571053504944},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.41151589155197144},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16634872555732727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10924527049064636},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08809003233909607},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2112912048","https://openalex.org/W2131774270","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2558460151","https://openalex.org/W2603705233","https://openalex.org/W2739181657","https://openalex.org/W2745461083","https://openalex.org/W2772385709","https://openalex.org/W2778940641","https://openalex.org/W2866343820","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2963403868","https://openalex.org/W2963467339","https://openalex.org/W2963521239","https://openalex.org/W2963668159","https://openalex.org/W2964120214","https://openalex.org/W2964121744","https://openalex.org/W3004349648","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6676647902","https://openalex.org/W6695709487","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6741383107","https://openalex.org/W6749537441","https://openalex.org/W6752083267","https://openalex.org/W6753640285"],"related_works":["https://openalex.org/W2371905728","https://openalex.org/W2358103843","https://openalex.org/W2356087601","https://openalex.org/W3168863246","https://openalex.org/W2177345753","https://openalex.org/W154629204","https://openalex.org/W2902304614","https://openalex.org/W1480228708","https://openalex.org/W3101291207","https://openalex.org/W3097751442"],"abstract_inverted_index":{"Exploring":[0],"the":[1,41,47,50,63,116,127,134],"entity-level":[2,70,109],"(i.e.,":[3],"objects":[4,67,85],"in":[5,9,25,86,133],"an":[6],"image,":[7],"words":[8],"a":[10,87,120],"text)":[11],"spatial":[12,23,71,81],"relationship":[13],"contributes":[14,106],"to":[15,30,55,68,96,107,125],"understanding":[16],"multimedia":[17],"content":[18],"precisely.":[19],"The":[20,92],"ignorance":[21],"of":[22,32,66,83,112,122,130],"information":[24],"previous":[26],"works":[27],"probably":[28],"leads":[29],"misunderstandings":[31],"image":[33,84,98],"contents.":[34],"For":[35],"instance,":[36],"sentences":[37],"`Boats":[38,44],"are":[39,45],"on":[40,144],"water'":[42,48],"and":[43,80,100,146],"under":[46],"describe":[49],"same":[51],"objects,":[52],"but":[53],"correspond":[54],"different":[56],"sceneries.":[57],"To":[58],"this":[59],"end,":[60],"we":[61,77],"utilize":[62],"relative":[64],"position":[65],"capture":[69],"relationships":[72,82],"for":[73],"image-text":[74,113,131],"matching.":[75],"Specifically,":[76],"fuse":[78],"semantic":[79],"visual":[88],"intra-modal":[89],"relation":[90,136],"module.":[91,137],"module":[93],"performs":[94],"promisingly":[95],"understand":[97],"contents":[99],"improve":[101],"object":[102],"representation":[103],"learning.":[104],"It":[105],"capturing":[108],"latent":[110],"correspondence":[111],"pairs.":[114],"Then":[115],"query":[117],"(text)":[118],"plays":[119],"role":[121],"textual":[123],"context":[124],"refine":[126],"interpretable":[128],"alignments":[129],"pairs":[132],"inter-modal":[135],"Our":[138],"proposed":[139],"method":[140],"achieves":[141],"state-of-the-art":[142],"results":[143],"MSCOCO":[145],"Flickr30K":[147],"datasets.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}