{"id":"https://openalex.org/W4284698859","doi":"https://doi.org/10.1145/3477495.3531715","title":"Where Does the Performance Improvement Come From?","display_name":"Where Does the Performance Improvement Come From?","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4284698859","doi":"https://doi.org/10.1145/3477495.3531715"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531715","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053687590","display_name":"Jun Rao","orcid":"https://orcid.org/0000-0001-5804-1508"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Rao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["China University of Petroleum (East China), qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456723","display_name":"Liang Ding","orcid":"https://orcid.org/0000-0001-8976-2084"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Ding","raw_affiliation_strings":["JD Explore Academy, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy, beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050911130","display_name":"Shuhan Qi","orcid":"https://orcid.org/0000-0002-6903-145X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhan Qi","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy, beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444156","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-5388-9080"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["China University of Petroleum (East China), qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China), qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["JD Explore Academy, beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy, beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6637,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89777806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2727","last_page":"2737"},"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":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996999979019165,"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":0.8198819160461426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7538347244262695},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7182146906852722},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6311497092247009},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.601844072341919},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6009401082992554},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5475006699562073},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5457921624183655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4535970091819763},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.44958072900772095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4000293016433716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198819160461426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7538347244262695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7182146906852722},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6311497092247009},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.601844072341919},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6009401082992554},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5475006699562073},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5457921624183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4535970091819763},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.44958072900772095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4000293016433716},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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:10.1145/3477495.3531715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531715","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3214728010","display_name":"\u57fa\u4e8e\u591a\u89c6\u89d2\u6df1\u5ea6\u7a00\u758f\u7f16\u7801\u53ca\u6d41\u5f62\u6b63\u5219\u5316\u7684\u56fe\u50cf\u6807\u6ce8\u7814\u7a76","funder_award_id":"61671480","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":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2069870183","https://openalex.org/W2131774270","https://openalex.org/W2141362318","https://openalex.org/W2185175083","https://openalex.org/W2481240925","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2897457738","https://openalex.org/W2963988212","https://openalex.org/W2998356391","https://openalex.org/W3034998639","https://openalex.org/W3035497460","https://openalex.org/W3105486918","https://openalex.org/W3118694826","https://openalex.org/W3173220247","https://openalex.org/W3173367141","https://openalex.org/W3175740157","https://openalex.org/W3175919386","https://openalex.org/W3209108016","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"This":[0],"article":[1],"aims":[2],"to":[3,27,89,106,125],"provide":[4,94],"the":[5,20,28,34,47,70,112,115,118,121],"information":[6,50],"retrieval":[7,16,24,38,58],"community":[8],"with":[9,77],"some":[10],"reflections":[11],"on":[12,75,111],"recent":[13],"advances":[14],"in":[15,46,69,83,133],"learning":[17],"by":[18,128],"analyzing":[19],"reproducibility":[21,113],"of":[22,30,49,86,114,120],"image-text":[23,37,57],"models.":[25],"Due":[26],"increase":[29],"multimodal":[31,102],"data":[32],"over":[33],"last":[35],"decade,":[36],"has":[39,72],"steadily":[40],"become":[41],"a":[42,84],"major":[43],"research":[44],"direction":[45],"field":[48],"retrieval.":[51],"Numerous":[52],"researchers":[53],"train":[54],"and":[55,66,98,117,130,136],"evaluate":[56],"algorithms":[59],"using":[60],"benchmark":[61],"datasets":[62],"such":[63],"as":[64],"MS-COCO":[65],"Flickr30k.":[67],"Research":[68],"past":[71],"mostly":[73],"focused":[74],"performance,":[76],"multiple":[78],"state-of-the-art":[79],"methodologies":[80],"being":[81],"suggested":[82],"variety":[85],"ways.":[87],"According":[88],"their":[90],"assertions,":[91],"these":[92],"techniques":[93],"improved":[95,126],"modality":[96],"interactions":[97],"hence":[99],"more":[100],"precise":[101],"representations.":[103],"In":[104],"contrast":[105],"previous":[107],"works,":[108],"we":[109],"focus":[110],"approaches":[116],"examination":[119],"elements":[122],"that":[123],"lead":[124],"performance":[127],"pretrained":[129],"nonpretrained":[131],"models":[132],"retrieving":[134],"images":[135],"text.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}