{"id":"https://openalex.org/W3033697199","doi":"https://doi.org/10.1145/3372278.3390709","title":"Visual Relations Augmented Cross-modal Retrieval","display_name":"Visual Relations Augmented Cross-modal Retrieval","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033697199","doi":"https://doi.org/10.1145/3372278.3390709","mag":"3033697199"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","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/A5067749750","display_name":"Yutian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yutian Guo","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396885","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2928-2692"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067749750"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.4655,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84430665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"15"},"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9979000091552734,"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":0.7987737655639648},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5833092927932739},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5375473499298096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283297300338745},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.521817147731781},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5198748111724854},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5095019936561584},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4939747452735901},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4907416105270386},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4875573515892029},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47550565004348755},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4691578149795532},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4622814953327179},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42549076676368713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520233929157257},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34898459911346436},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29102474451065063},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17125356197357178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987737655639648},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5833092927932739},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5375473499298096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283297300338745},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.521817147731781},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5198748111724854},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5095019936561584},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4939747452735901},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4907416105270386},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4875573515892029},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47550565004348755},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4691578149795532},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4622814953327179},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42549076676368713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520233929157257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34898459911346436},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29102474451065063},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17125356197357178},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1964073652","https://openalex.org/W2077069816","https://openalex.org/W2112912048","https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2346425926","https://openalex.org/W2546696630","https://openalex.org/W2579549467","https://openalex.org/W2603705233","https://openalex.org/W2607855566","https://openalex.org/W2765440071","https://openalex.org/W2778100917","https://openalex.org/W2798782720","https://openalex.org/W2806331055","https://openalex.org/W2886970679","https://openalex.org/W2894786240","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963184176","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2964120214","https://openalex.org/W2981448908","https://openalex.org/W3029678209","https://openalex.org/W3147309958"],"related_works":["https://openalex.org/W2952745240","https://openalex.org/W4301143707","https://openalex.org/W2949074159","https://openalex.org/W4298715519","https://openalex.org/W2474574787","https://openalex.org/W4386094778","https://openalex.org/W1926504679","https://openalex.org/W2111997505","https://openalex.org/W2399159263","https://openalex.org/W1581578909"],"abstract_inverted_index":{"Retrieving":[0],"relevant":[1,50],"samples":[2,51],"across":[3],"multiple-modalities":[4],"is":[5],"a":[6,34,100],"primary":[7],"topic":[8],"that":[9,103],"receives":[10],"consistently":[11],"research":[12],"interests":[13],"in":[14,57,71,76],"multimedia":[15,22],"communities,":[16],"and":[17,141,155],"has":[18],"benefited":[19],"various":[20],"real-world":[21],"applications":[23],"(e.g.,":[24],"text-based":[25],"image":[26],"searching).":[27],"Current":[28],"models":[29,63],"mainly":[30],"focus":[31],"on":[32,151],"learning":[33,72,133],"unified":[35],"visual":[36,42,69,73,85,96,105,112,134],"semantic":[37],"embedding":[38,59],"space":[39],"to":[40],"bridge":[41],"contents":[43],"&":[44],"text":[45],"query,":[46],"targeting":[47],"at":[48],"aligning":[49],"from":[52,121],"different":[53,88],"modalities":[54],"as":[55],"neighbors":[56],"the":[58,83,117,127,139,152,160],"space.":[60],"However,":[61],"these":[62],"did":[64],"not":[65],"consider":[66],"relations":[67,89,108,113],"between":[68,109],"components":[70,86],"representations,":[74],"resulting":[75],"their":[77],"incapability":[78],"of":[79,162],"distinguishing":[80],"images":[81],"with":[82,107],"same":[84],"but":[87],"(i.e.,":[90],"Figure":[91],"1).":[92],"To":[93],"precisely":[94],"modeling":[95],"contents,":[97],"we":[98],"introduce":[99],"novel":[101],"framework":[102],"enhanced":[104],"representation":[106,143],"components.":[110],"Specifically,":[111],"are":[114],"represented":[115],"by":[116,126],"scene":[118],"graph":[119,128],"extracted":[120],"an":[122],"image,":[123],"then":[124],"encoded":[125],"convolutional":[129],"neural":[130],"networks":[131],"for":[132,145,166],"relational":[135,140],"features.":[136],"We":[137],"combine":[138],"compositional":[142],"together":[144],"image-text":[146],"retrieval.":[147],"Empirical":[148],"results":[149],"conducted":[150],"challenging":[153],"MS-COCO":[154],"Flicker":[156],"30K":[157],"datasets":[158],"demonstrate":[159],"effectiveness":[161],"our":[163],"proposed":[164],"model":[165],"cross-modal":[167],"retrieval":[168],"task.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}