{"id":"https://openalex.org/W4312823189","doi":"https://doi.org/10.1109/tmm.2022.3222653","title":"Caption-Aided Product Detection via Collaborative Pseudo-Label Harmonization","display_name":"Caption-Aided Product Detection via Collaborative Pseudo-Label Harmonization","publication_year":2022,"publication_date":"2022-11-16","ids":{"openalex":"https://openalex.org/W4312823189","doi":"https://doi.org/10.1109/tmm.2022.3222653"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3222653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3222653","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5101961088","display_name":"Xiao Dong","orcid":"https://orcid.org/0000-0001-9519-612X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Dong","raw_affiliation_strings":["Sun Yat-Sen University, Zhuhai, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9519-612X","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048961496","display_name":"Gengwei Zhang","orcid":"https://orcid.org/0000-0003-1823-502X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gengwei Zhang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1823-502X","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049388503","display_name":"Xunlin Zhan","orcid":"https://orcid.org/0000-0001-5053-7349"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunlin Zhan","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433191","display_name":"Yi Ding","orcid":"https://orcid.org/0000-0002-6774-4536"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6774-4536","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2812-8781","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037966954","display_name":"Minlong Lu","orcid":"https://orcid.org/0000-0002-9851-6480"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minlong Lu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54387032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"1916","last_page":"1927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.9988999962806702,"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":0.74062180519104},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.6243321895599365},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5429418683052063},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5373361110687256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49944353103637695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35875511169433594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3448195457458496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13943696022033691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74062180519104},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.6243321895599365},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5429418683052063},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5373361110687256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49944353103637695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35875511169433594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3448195457458496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13943696022033691},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3222653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3222653","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4320043517","display_name":null,"funder_award_id":"RCYX20200714114642083","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G517407545","display_name":null,"funder_award_id":"61976233","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5604801150","display_name":null,"funder_award_id":"JCYJ20190807154211365","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W318792885","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1994488211","https://openalex.org/W2016016818","https://openalex.org/W2088049833","https://openalex.org/W2124351162","https://openalex.org/W2154318594","https://openalex.org/W2194775991","https://openalex.org/W2519284461","https://openalex.org/W2579710467","https://openalex.org/W2604260814","https://openalex.org/W2606831796","https://openalex.org/W2610510511","https://openalex.org/W2798748179","https://openalex.org/W2813911573","https://openalex.org/W2884195989","https://openalex.org/W2896457183","https://openalex.org/W2920292591","https://openalex.org/W2963150697","https://openalex.org/W2963271314","https://openalex.org/W2963516811","https://openalex.org/W2963603913","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2981613027","https://openalex.org/W2982103617","https://openalex.org/W2982905682","https://openalex.org/W2989514282","https://openalex.org/W2991023920","https://openalex.org/W2991662170","https://openalex.org/W2997544875","https://openalex.org/W3014494055","https://openalex.org/W3023138874","https://openalex.org/W3035725370","https://openalex.org/W3044511083","https://openalex.org/W3100622326","https://openalex.org/W3104770333","https://openalex.org/W3113075965","https://openalex.org/W3126337491","https://openalex.org/W3166396011","https://openalex.org/W4287658071","https://openalex.org/W4290065491","https://openalex.org/W4297971002","https://openalex.org/W4301372783","https://openalex.org/W6600313631","https://openalex.org/W6611089629","https://openalex.org/W6639102338","https://openalex.org/W6683033130","https://openalex.org/W6726508743","https://openalex.org/W6732909215","https://openalex.org/W6753280777","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6781207254","https://openalex.org/W6783983736","https://openalex.org/W6783990618","https://openalex.org/W6785700261","https://openalex.org/W6790019176","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Product":[0],"detection,":[1],"which":[2,68],"aims":[3],"to":[4,56,126,131,187],"localize":[5],"products":[6,44,115],"of":[7,29,114,174,191,220],"interest":[8],"in":[9,119,201],"the":[10,65,80,170,189,198,209,215,218,221,225],"advertising":[11,66],"images,":[12],"helps":[13],"advance":[14],"many":[15],"potential":[16],"E-commerce":[17,48,109],"applications":[18],"like":[19],"product":[20,31,35,60,103],"retrieval":[21],"and":[22,33,39,76,116,217],"recommendation.":[23],"However,":[24],"labeling":[25],"a":[26,58,86,91,133,144,178,202],"massive":[27],"number":[28],"fine-grained":[30,59,112],"categories":[32],"accurate":[34],"boxes":[36],"is":[37],"costly":[38],"especially":[40],"not":[41],"practical":[42],"since":[43],"are":[45,69,106],"ever-changing":[46],"on":[47,183,208],"websites.":[49,110],"In":[50],"this":[51,140],"work,":[52],"we":[53,89,142],"step":[54],"forward":[55],"train":[57,132],"detector":[61],"solely":[62],"supervised":[63,82,135,204],"by":[64],"captions,":[67],"naturally":[70],"available":[71],"but":[72],"often":[73],"severely":[74],"flawed":[75],"noisy.":[77],"To":[78,138],"reformulate":[79],"weakly":[81,134,203],"detection":[83],"research":[84],"into":[85],"real-world":[87],"setting,":[88],"introduce":[90],"large-scale":[92],"benchmark,":[93],"named":[94],"<italic":[95,120,210],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96,121,146,150,154,158,211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CapProduct</i>":[97,122,212],",":[98],"where":[99],"more":[100],"than":[101],"80,000":[102],"image-caption":[104],"pairs":[105],"collected":[107],"from":[108],"The":[111],"nature":[113],"noisy":[117],"captions":[118],"make":[123],"it":[124],"intractable":[125],"excavate":[127],"valid":[128],"category":[129],"labels":[130,167],"object":[136],"detector.":[137],"tackle":[139],"challenge,":[141],"propose":[143],"<bold":[145,149,153,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Co</b>":[147],"llaborative":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">P</b>":[151],"seudo-":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</b>":[155],"abel":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">H</b>":[159],"armonization":[160],"(CoPLH)":[161],"framework":[162],"that":[163],"harmonizes":[164],"self-mined":[165],"pseudo":[166],"via":[168],"modeling":[169],"global":[171],"co-occurrence":[172,180],"relationships":[173],"products.":[175],"We":[176],"construct":[177],"collaborative":[179],"graph":[181],"based":[182],"all":[184],"training":[185],"samples":[186],"improve":[188],"reliability":[190],"caption-predicted":[192],"pseudo-labels":[193],"as":[194,196],"well":[195],"benefit":[197],"self-training":[199],"procedure":[200],"setting.":[205],"Extensive":[206],"experiments":[207],"dataset":[213],"demonstrate":[214],"effectiveness":[216],"superiority":[219],"proposed":[222],"CoPLH":[223],"over":[224],"state-of-the-art":[226],"baselines.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}