{"id":"https://openalex.org/W2157530295","doi":"https://doi.org/10.1145/2647868.2654915","title":"Start from Scratch","display_name":"Start from Scratch","publication_year":2014,"publication_date":"2014-10-31","ids":{"openalex":"https://openalex.org/W2157530295","doi":"https://doi.org/10.1145/2647868.2654915","mag":"2157530295"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","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/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091587552","display_name":"Huanbo Luan","orcid":"https://orcid.org/0000-0003-3938-119X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huanbo Luan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuicheng Yang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042324027"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":7.0723,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.97840165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10824","display_name":"Image Retrieval and Classification 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8409076929092407},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5985326766967773},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5925484895706177},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5630785822868347},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5460456013679504},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5334776639938354},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.470305860042572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668956995010376},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.456041157245636},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4507298171520233},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4487707018852234},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4371466636657715},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.436541348695755},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41526585817337036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.327464759349823},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3023725748062134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409076929092407},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5985326766967773},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5925484895706177},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5630785822868347},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5460456013679504},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5334776639938354},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.470305860042572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668956995010376},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.456041157245636},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4507298171520233},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4487707018852234},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4371466636657715},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.436541348695755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41526585817337036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.327464759349823},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3023725748062134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2647868.2654915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7908339903","display_name":null,"funder_award_id":"R-252-300-001-490","funder_id":"https://openalex.org/F4320320749","funder_display_name":"Media Development Authority - Singapore"},{"id":"https://openalex.org/G8033733971","display_name":null,"funder_award_id":"61303075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320749","display_name":"Media Development Authority - Singapore","ror":"https://ror.org/00hhhdj49"},{"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":45,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1528802670","https://openalex.org/W1548802052","https://openalex.org/W1560724230","https://openalex.org/W1614298861","https://openalex.org/W1953590900","https://openalex.org/W1964763677","https://openalex.org/W1980287119","https://openalex.org/W1984541135","https://openalex.org/W2017198039","https://openalex.org/W2018573225","https://openalex.org/W2021166260","https://openalex.org/W2028891871","https://openalex.org/W2031342017","https://openalex.org/W2048012365","https://openalex.org/W2072128103","https://openalex.org/W2080171500","https://openalex.org/W2080722576","https://openalex.org/W2081553713","https://openalex.org/W2084435358","https://openalex.org/W2089150756","https://openalex.org/W2098411764","https://openalex.org/W2100495367","https://openalex.org/W2107698128","https://openalex.org/W2108598243","https://openalex.org/W2112274848","https://openalex.org/W2116825644","https://openalex.org/W2120615054","https://openalex.org/W2122528955","https://openalex.org/W2123737024","https://openalex.org/W2123921497","https://openalex.org/W2128487019","https://openalex.org/W2152444902","https://openalex.org/W2155541015","https://openalex.org/W2164587673","https://openalex.org/W2165232124","https://openalex.org/W2167057485","https://openalex.org/W2184161947","https://openalex.org/W2184188583","https://openalex.org/W2187223183","https://openalex.org/W2901058987","https://openalex.org/W2912622340","https://openalex.org/W2915649242","https://openalex.org/W3119651796","https://openalex.org/W4231109964"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Higher-level":[0],"semantics":[1],"such":[2,185],"as":[3,186,191],"visual":[4,70,101,114],"attributes":[5,26,123,157],"are":[6,64],"crucial":[7],"for":[8],"fundamental":[9],"multimedia":[10,171,183],"applications.":[11],"We":[12],"present":[13],"a":[14,68,82],"novel":[15,83],"attribute":[16,47,143],"discovery":[17,48,78],"approach":[18,51],"that":[19,36,92],"can":[20,37,93],"automatically":[21],"identify,":[22],"model":[23,132],"and":[24,33,59,102,115,124,137,139,164,176,189],"name":[25,141],"from":[27,45],"an":[28],"arbitrary":[29],"set":[30],"of":[31,108,162,178],"image":[32,163,187],"text":[34],"pairs":[35,161],"be":[38],"easily":[39],"gathered":[40],"on":[41,55,81,168],"the":[42,100,106,109,142,151,174,179,194],"Web.":[43],"Different":[44],"conventional":[46],"methods,":[49],"our":[50],"does":[52],"not":[53],"rely":[54],"any":[56,74],"pre-defined":[57],"vocabularies":[58],"human":[60,75,146],"labeling.":[61],"Therefore,":[62],"we":[63,118],"able":[65],"to":[66,120,193],"build":[67],"large":[69],"knowledge":[71],"base":[72],"without":[73],"efforts.":[76],"The":[77],"is":[79],"based":[80],"deep":[84],"architecture,":[85],"named":[86],"Independent":[87],"Component":[88],"Multimodal":[89],"Autoencoder":[90],"(ICMAE),":[91],"continually":[94],"learn":[95],"shared":[96],"higher-level":[97],"representations":[98,111],"across":[99],"textual":[103],"modalities.":[104],"With":[105],"help":[107],"resultant":[110],"encoding":[112],"strong":[113],"semantic":[116],"evidences,":[117],"propose":[119],"(a)":[121],"identify":[122],"their":[125],"corresponding":[126],"high-quality":[127],"training":[128],"images,":[129],"(b)":[130],"iteratively":[131],"them":[133],"with":[134,145],"maximum":[135],"compactness":[136],"comprehensiveness,":[138],"(c)":[140],"models":[144],"understandable":[147],"words.":[148],"To":[149],"date,":[150],"proposed":[152],"system":[153],"has":[154],"discovered":[155,180],"1,898":[156],"over":[158],"1.3":[159],"million":[160],"text.":[165],"Extensive":[166],"experiments":[167],"various":[169],"real-world":[170],"datasets":[172],"demonstrate":[173],"quality":[175],"effectiveness":[177],"attributes,":[181],"facilitating":[182],"applications":[184],"annotation":[188],"retrieval":[190],"compared":[192],"state-of-the-art":[195],"approaches.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}