{"id":"https://openalex.org/W4385624386","doi":"https://doi.org/10.1109/icufn57995.2023.10200668","title":"Multi-modal Fine-grained Retrieval with Local and Global Cross-Attention","display_name":"Multi-modal Fine-grained Retrieval with Local and Global Cross-Attention","publication_year":2023,"publication_date":"2023-07-04","ids":{"openalex":"https://openalex.org/W4385624386","doi":"https://doi.org/10.1109/icufn57995.2023.10200668"},"language":"en","primary_location":{"id":"doi:10.1109/icufn57995.2023.10200668","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icufn57995.2023.10200668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN)","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/A5072153328","display_name":"Qiaosong Chen","orcid":"https://orcid.org/0000-0002-4763-5359"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiaosong Chen","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449291","display_name":"Ye Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Zhang","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075483337","display_name":"Junzhuo Liu","orcid":"https://orcid.org/0000-0002-5155-5781"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhuo Liu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700403","display_name":"Zhixiang Wang","orcid":"https://orcid.org/0000-0002-4778-7539"},"institutions":[{"id":"https://openalex.org/I2800191616","display_name":"Maastricht University Medical Centre","ror":"https://ror.org/02d9ce178","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800191616"]},{"id":"https://openalex.org/I4210161616","display_name":"Maastro Clinic","ror":"https://ror.org/059wkzj26","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I4210161616"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhixiang Wang","raw_affiliation_strings":["GROW-School Maastricht University Medical Centre+,Department of Radiation Oncology (Maastro),Maastricht,The Netherlands"],"affiliations":[{"raw_affiliation_string":"GROW-School Maastricht University Medical Centre+,Department of Radiation Oncology (Maastro),Maastricht,The Netherlands","institution_ids":["https://openalex.org/I4210161616","https://openalex.org/I2800191616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650157","display_name":"Xin Deng","orcid":"https://orcid.org/0000-0003-1257-694X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Deng","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346212","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0003-3106-021X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Data Engineering and Visual Computing,Chongqing,P.R.China,400065","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072153328"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.1206,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40173656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9916999936103821,"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":0.7834571599960327},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7441611289978027},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6315903067588806},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6267648935317993},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5689648389816284},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5596501231193542},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.530879020690918},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5182311534881592},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4985237121582031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4642319083213806},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4424581825733185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4174572229385376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40620002150535583},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37654343247413635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1785092055797577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834571599960327},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7441611289978027},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6315903067588806},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6267648935317993},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5689648389816284},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5596501231193542},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.530879020690918},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5182311534881592},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4985237121582031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4642319083213806},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4424581825733185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4174572229385376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40620002150535583},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37654343247413635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1785092055797577},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icufn57995.2023.10200668","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icufn57995.2023.10200668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:publications/128df9bb-e0c2-4553-aeba-4a633d2102b0","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/128df9bb-e0c2-4553-aeba-4a633d2102b0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, Q, Zhang, Y, Liu, J, Wang, Z, Deng, X & Wang, J 2023, Multi-modal Fine-grained Retrieval with Local and Global Cross-Attention. in ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks. 1 edn, IEEE Xplore, International Conference on Ubiquitous and Future Networks, ICUFN, vol. 2023-July, pp. 1-7, 14th International Conference on Ubiquitous and Future Networks, Paris, France, 4/07/23. https://doi.org/10.1109/ICUFN57995.2023.10200668","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2013535308","https://openalex.org/W2574447816","https://openalex.org/W2740755807","https://openalex.org/W2752782242","https://openalex.org/W2765440071","https://openalex.org/W2791528017","https://openalex.org/W2805903690","https://openalex.org/W2807978488","https://openalex.org/W2808711976","https://openalex.org/W2891355224","https://openalex.org/W2896457183","https://openalex.org/W2909384861","https://openalex.org/W2956335072","https://openalex.org/W2964130424","https://openalex.org/W2981413347","https://openalex.org/W3034445277","https://openalex.org/W3094502228","https://openalex.org/W3096121022","https://openalex.org/W3096609285","https://openalex.org/W3103717910","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3186542922","https://openalex.org/W4206237889","https://openalex.org/W4206322350","https://openalex.org/W4312810944","https://openalex.org/W4385245566","https://openalex.org/W4403481522","https://openalex.org/W6732292492","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778485988","https://openalex.org/W6779879114","https://openalex.org/W6784333009","https://openalex.org/W6790690058","https://openalex.org/W6804138277"],"related_works":["https://openalex.org/W2172231696","https://openalex.org/W2089969684","https://openalex.org/W2002918846","https://openalex.org/W627697492","https://openalex.org/W2503910294","https://openalex.org/W2384506582","https://openalex.org/W2034539438","https://openalex.org/W2130191173","https://openalex.org/W1787428848","https://openalex.org/W2188202313"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,71,144],"cross-modal":[3,34],"retrieval":[4,35,92],"is":[5,42],"that":[6,167],"the":[7,17,28,33,60,69,75,95,126,140,154,173],"user":[8],"gives":[9],"any":[10],"sample":[11,80],"as":[12,59],"a":[13,88,113],"query":[14,29],"sample,":[15],"and":[16,20,63,74,102,109,120,128,151,163],"system":[18],"retrieves":[19],"feeds":[21],"back":[22],"various":[23],"modal":[24,135],"samples":[25],"related":[26],"to":[27,124],"sample.":[30],"At":[31],"present,":[32],"method":[36,93,169],"mainly":[37],"focuses":[38],"on":[39,172],"coarse-grained,":[40],"which":[41,98,137],"far":[43],"from":[44,106],"being":[45],"satisfied":[46],"in":[47,55,78,112],"practical":[48],"application.":[49],"However,":[50],"there":[51],"are":[52],"many":[53],"difficulties":[54],"fine-grained":[56,79,91],"retrieval,":[57],"such":[58],"heterogeneous":[61],"gap":[62,65,155],"semantic":[64],"between":[66,156],"multi-modal":[67,90],"data,":[68,136],"difficulty":[70],"similarity":[72],"measurement,":[73],"small":[76],"difference":[77],"features.":[81],"To":[82],"overcome":[83],"these":[84],"limitations,":[85],"we":[86,117],"propose":[87],"novel":[89],"with":[94],"LAGC-Attention":[96],"module,":[97],"can":[99],"fully":[100],"extract":[101,125],"fuse":[103],"feature":[104,141,158],"information":[105,131],"different":[107,157],"modalities":[108],"represent":[110],"them":[111],"common":[114],"space.":[115],"Specifically,":[116],"use":[118],"local":[119],"global":[121,129],"cross":[122],"self-attention":[123],"neighboring":[127],"context":[130],"for":[132],"each":[133,145],"single":[134],"greatly":[138],"enhances":[139],"representation":[142],"capability":[143],"modality":[146],"(image,":[147],"text,":[148],"audio,":[149],"video),":[150],"especially":[152],"reduce":[153],"distributions.":[159],"Finally,":[160],"Extensive":[161],"experiments":[162],"ablation":[164],"studies":[165],"demonstrate":[166],"our":[168],"achieves":[170],"state-of-the-art":[171],"public":[174],"dataset":[175],"PKU":[176],"FG-XMedia.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}