{"id":"https://openalex.org/W2964081303","doi":"https://doi.org/10.1109/tip.2018.2852503","title":"Modality-Specific Cross-Modal Similarity Measurement With Recurrent Attention Network","display_name":"Modality-Specific Cross-Modal Similarity Measurement With Recurrent Attention Network","publication_year":2018,"publication_date":"2018-07-02","ids":{"openalex":"https://openalex.org/W2964081303","doi":"https://doi.org/10.1109/tip.2018.2852503","mag":"2964081303","pmid":"https://pubmed.ncbi.nlm.nih.gov/29994397"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2852503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2852503","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/A5114231005","display_name":"Yuxin Peng","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":"Yuxin Peng","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026142528","display_name":"Jinwei Qi","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":"Jinwei Qi","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017074356","display_name":"Yuxin Yuan","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":"Yuxin Yuan","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114231005"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":7.3309,"has_fulltext":false,"cited_by_count":156,"citation_normalized_percentile":{"value":0.97887173,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"27","issue":"11","first_page":"5585","last_page":"5599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9970999956130981,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6830347776412964},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6573915481567383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5566613078117371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522489547729492},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4913603365421295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4157492220401764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3581395149230957},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12172845005989075}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6830347776412964},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6573915481567383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5566613078117371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522489547729492},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4913603365421295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4157492220401764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3581395149230957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12172845005989075},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2018.2852503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2852503","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:29994397","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29994397","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":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7072385062","display_name":null,"funder_award_id":"61532005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8355516938","display_name":null,"funder_award_id":"61771025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1491300635","https://openalex.org/W1514535095","https://openalex.org/W1523385540","https://openalex.org/W1544827683","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1904365287","https://openalex.org/W1925193522","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W1964073652","https://openalex.org/W1997107867","https://openalex.org/W2013535308","https://openalex.org/W2022398331","https://openalex.org/W2025341678","https://openalex.org/W2052727801","https://openalex.org/W2053667957","https://openalex.org/W2064675550","https://openalex.org/W2070753207","https://openalex.org/W2090575037","https://openalex.org/W2100235303","https://openalex.org/W2106277773","https://openalex.org/W2114456882","https://openalex.org/W2118463056","https://openalex.org/W2119775030","https://openalex.org/W2126523478","https://openalex.org/W2138118304","https://openalex.org/W2147527908","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2210322478","https://openalex.org/W2211092169","https://openalex.org/W2217869562","https://openalex.org/W2295088417","https://openalex.org/W2326180695","https://openalex.org/W2342543219","https://openalex.org/W2463565445","https://openalex.org/W2468048057","https://openalex.org/W2476624367","https://openalex.org/W2526479943","https://openalex.org/W2557865186","https://openalex.org/W2574447816","https://openalex.org/W2589728353","https://openalex.org/W2591669147","https://openalex.org/W2605649771","https://openalex.org/W2606965845","https://openalex.org/W2766910785","https://openalex.org/W2949615363","https://openalex.org/W2951527505","https://openalex.org/W2962741254","https://openalex.org/W2962835968","https://openalex.org/W2962958286","https://openalex.org/W2962965405","https://openalex.org/W2963668159","https://openalex.org/W2963954913","https://openalex.org/W4251308012","https://openalex.org/W4294170691","https://openalex.org/W6630875275","https://openalex.org/W6631216910","https://openalex.org/W6632455782","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6639118987","https://openalex.org/W6682137061","https://openalex.org/W6682691769","https://openalex.org/W6684191040","https://openalex.org/W6686207219","https://openalex.org/W6697562861","https://openalex.org/W6719057275","https://openalex.org/W6730042849","https://openalex.org/W6732292492"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W627697492","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Nowadays,":[0],"cross-modal":[1,30,106,178,209,213],"retrieval":[2],"plays":[3],"an":[4,122],"important":[5],"role":[6],"to":[7,89,126,211],"flexibly":[8],"find":[9,90],"useful":[10],"information":[11,50],"across":[12],"different":[13,22,87,189,199],"modalities":[14,23,33,200],"of":[15,24,29,49,155,206,235],"data.":[16],"Effectively":[17],"measuring":[18],"the":[19,27,53,91,113,153,170,176,183,192,195,207,217,233],"similarity":[20,107,131],"between":[21,94,188,194],"data":[25,154],"is":[26,158,201],"key":[28],"retrieval.":[31,214],"Different":[32],"such":[34],"as":[35,224,226],"image":[36],"and":[37,41,44,70,181,185],"text":[38],"have":[39],"imbalanced":[40,184],"complementary":[42,186],"relationship,":[43],"they":[45],"contain":[46,60],"unequal":[47],"amount":[48],"when":[51],"describing":[52],"same":[54],"semantics.":[55],"For":[56,136],"example,":[57],"images":[58],"often":[59],"more":[61],"details":[62],"that":[63],"cannot":[64],"be":[65],"demonstrated":[66],"by":[67,111,148,203],"textual":[68],"descriptions":[69],"vice":[71],"versa.":[72],"Existing":[73],"works":[74],"based":[75,165],"on":[76,216],"Deep":[77],"Neural":[78],"Network":[79],"(DNN)":[80],"mostly":[81],"construct":[82],"one":[83,143],"common":[84,134],"space":[85,116,162],"for":[86,117,174,198],"modalities,":[88],"latent":[92],"alignments":[93],"them,":[95],"which":[96,120,168],"lose":[97],"their":[98],"exclusive":[99],"modality-specific":[100,105,129,140,208],"characteristics.":[101],"Therefore,":[102],"we":[103],"propose":[104],"measurement":[108],"(MCSM)":[109],"approach":[110],"constructing":[112],"independent":[114],"semantic":[115,138,196],"each":[118,137],"modality,":[119],"adopts":[121],"endto-":[123],"end":[124],"framework":[125],"directly":[127],"generate":[128],"crossmodal":[130],"without":[132],"explicit":[133],"representation.":[135],"space,":[139],"characteristics":[141],"within":[142],"modality":[144,157],"are":[145],"fully":[146],"exploited":[147],"recurrent":[149],"attention":[150,164,172],"network,":[151],"while":[152],"another":[156],"projected":[159],"into":[160],"this":[161],"with":[163],"joint":[166],"embedding,":[167],"utilizes":[169],"learned":[171],"weights":[173],"guiding":[175],"fine-grained":[177],"correlation":[179],"learning,":[180],"captures":[182],"relationship":[187],"modalities.":[190],"Finally,":[191],"complementarity":[193],"spaces":[197],"explored":[202],"adaptive":[204],"fusion":[205],"similarities":[210],"perform":[212],"Experiments":[215],"widely-used":[218],"Wikipedia,":[219],"Pascal":[220],"Sentence,":[221],"MS-COCO":[222],"datasets":[223],"well":[225],"our":[227,236],"constructed":[228],"large-scale":[229],"XMediaNet":[230],"dataset":[231],"verify":[232],"effectiveness":[234],"proposed":[237],"approach,":[238],"outperforming":[239],"9":[240],"stateof-":[241],"the-art":[242],"methods.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}