{"id":"https://openalex.org/W3201645700","doi":"https://doi.org/10.1145/3512527.3531368","title":"Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval","display_name":"Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W3201645700","doi":"https://doi.org/10.1145/3512527.3531368","mag":"3201645700"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","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/A5078689432","display_name":"Zhihao Fan","orcid":"https://orcid.org/0000-0002-9910-7937"},"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":"Zhihao Fan","raw_affiliation_strings":["Fudan University, Shanghai, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, UNK, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011504177","display_name":"Zhongyu Wei","orcid":"https://orcid.org/0000-0003-3789-8507"},"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":"Zhongyu Wei","raw_affiliation_strings":["Fudan University, Shanghai, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, UNK, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725946","display_name":"Zejun Li","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":false,"raw_author_name":"Zejun Li","raw_affiliation_strings":["Fudan University, Shanghai, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, UNK, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440548","display_name":"Siyuan Wang","orcid":"https://orcid.org/0000-0002-5036-0608"},"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":"Siyuan Wang","raw_affiliation_strings":["Fudan University, Shanghai, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, UNK, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103943513","display_name":"Haijun Shan","orcid":"https://orcid.org/0000-0001-5693-6084"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Shan","raw_affiliation_strings":["Zhejiang Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111113722","display_name":"Xuanjing Huang","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":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, UNK, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, UNK, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075631505","display_name":"Jianqing Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianqing Fan","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078689432"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.1224,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.77896929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"145"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9961000084877014,"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":0.9958999752998352,"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":0.8414400815963745},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7074637413024902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7001837491989136},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6351344585418701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6188384890556335},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5226806998252869},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4529619514942169},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40941542387008667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414400815963745},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7074637413024902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7001837491989136},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6351344585418701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6188384890556335},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5226806998252869},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4529619514942169},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40941542387008667},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1957706851","https://openalex.org/W2123024445","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2546696630","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2750779823","https://openalex.org/W2798280084","https://openalex.org/W2949792119","https://openalex.org/W2962964995","https://openalex.org/W2963101956","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963499204","https://openalex.org/W2963652649","https://openalex.org/W2964121744","https://openalex.org/W2965848243","https://openalex.org/W2966683369","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2998215884","https://openalex.org/W2998356391","https://openalex.org/W3010277541","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3090449556","https://openalex.org/W3173220247","https://openalex.org/W3206597437"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2039546652","https://openalex.org/W4281476908"],"abstract_inverted_index":{"Existing":[0],"research":[1],"for":[2,17,47,65,79,110],"image":[3,26,68],"text":[4,76],"retrieval":[5],"mainly":[6],"relies":[7],"on":[8,157],"sentence-level":[9,71,99],"supervision":[10,46,97],"to":[11,42,94,124,168],"distinguish":[12],"matched":[13,81],"and":[14,27,72,83,86,100,136,148,151,159],"mismatched":[15,52,153],"sentences":[16,28,82],"a":[18,66],"query":[19,67],"image.":[20],"However,":[21],"semantic":[22,60,129],"mismatch":[23],"between":[24],"an":[25],"usually":[29],"happens":[30],"in":[31,54,69,131],"finer":[32],"grain,":[33],"i.e.,":[34],"phrase":[35],"level.":[36],"In":[37,57,92],"this":[38],"paper,":[39],"we":[40,102,117,141],"explore":[41],"introduce":[43],"additional":[44],"phrase-level":[45,90],"the":[48,55,80,89,115,139,162],"better":[49],"identification":[50],"of":[51,98,121,127,134,164],"units":[53,130],"text.":[56],"practice,":[58],"multi-grained":[59,128],"labels":[61],"are":[62],"automatically":[63],"constructed":[64],"both":[70,96,132,146],"phrase-level.":[73],"We":[74],"construct":[75],"scene":[77],"graphs":[78],"extract":[84],"entities":[85],"triples":[87],"as":[88],"labels.":[91],"order":[93],"integrate":[95],"phrase-level,":[101],"propose":[103,142],"Semantic":[104],"Structure":[105],"Aware":[106],"Multimodal":[107],"Transformer":[108],"(SSAMT)":[109],"multi-modal":[111],"representation":[112],"learning.":[113],"Inside":[114],"SSAMT,":[116],"utilize":[118],"different":[119],"kinds":[120],"attention":[122],"mechanisms":[123],"enforce":[125],"interactions":[126],"sides":[133],"vision":[135],"language.":[137],"For":[138],"training,":[140],"multi-scale":[143],"matching":[144],"from":[145],"global":[147],"local":[149],"perspectives,":[150],"penalize":[152],"phrases.":[154],"Experimental":[155],"results":[156],"MS-COCO":[158],"Flickr30K":[160],"show":[161],"effectiveness":[163],"our":[165],"approach":[166],"compared":[167],"some":[169],"state-of-the-art":[170],"models.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}