{"id":"https://openalex.org/W2139832588","doi":"https://doi.org/10.1109/icassp.2008.4517738","title":"Learning object classes from image thumbnails through deep neural networks","display_name":"Learning object classes from image thumbnails through deep neural networks","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2139832588","doi":"https://doi.org/10.1109/icassp.2008.4517738","mag":"2139832588"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4517738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517738","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5081351856","display_name":"Erkang Chen","orcid":"https://orcid.org/0000-0003-1577-1732"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Erkang Chen","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Institute for Computer Science, University of Freiburg, Germany","Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Institute for Computer Science, University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046703129","display_name":"Hongyuan Zha","orcid":"https://orcid.org/0000-0001-7493-0911"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422075","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-6974-5516"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447806","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0001-8799-1182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zhang","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081351856"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.4207,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.51932239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/thumbnail","display_name":"Thumbnail","score":0.9459244012832642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822877824306488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6849980354309082},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6557440757751465},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6220614314079285},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5857561826705933},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.5594731569290161},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5324493646621704},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5281365513801575},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5024228096008301},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4994819164276123},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4814169108867645},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4735022187232971},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45419955253601074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4513515532016754},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4376908838748932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4280095100402832}],"concepts":[{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.9459244012832642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822877824306488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6849980354309082},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6557440757751465},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6220614314079285},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5857561826705933},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.5594731569290161},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5324493646621704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5281365513801575},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5024228096008301},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4994819164276123},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4814169108867645},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4735022187232971},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45419955253601074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4513515532016754},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4376908838748932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4280095100402832},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4517738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517738","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1487601331","https://openalex.org/W1607198972","https://openalex.org/W2030536784","https://openalex.org/W2100495367","https://openalex.org/W2110798204","https://openalex.org/W2115733720","https://openalex.org/W2152469116","https://openalex.org/W2154422044","https://openalex.org/W2157716919","https://openalex.org/W3140968660","https://openalex.org/W4285719527","https://openalex.org/W6629001579","https://openalex.org/W6682394276"],"related_works":["https://openalex.org/W137154299","https://openalex.org/W2011506639","https://openalex.org/W2095080241","https://openalex.org/W2501702011","https://openalex.org/W2908847257","https://openalex.org/W2512435841","https://openalex.org/W4298160414","https://openalex.org/W4246915297","https://openalex.org/W2951675648","https://openalex.org/W2951818954"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"new":[3],"approach":[4,46,88,105],"for":[5],"recognizing":[6],"object":[7],"classes":[8],"which":[9,37],"is":[10,89],"based":[11,63],"on":[12,64,76],"the":[13,23,69,77,86,103,108,111,114,117],"intuitive":[14],"idea":[15],"that":[16,85],"human":[17],"beings":[18],"are":[19],"able":[20],"to":[21,91],"perform":[22],"task":[24],"well":[25],"given":[26],"only":[27],"thumbnails":[28,48],"(coarse":[29],"scale":[30],"version)":[31],"of":[32,72,79,98,102,110,116],"images.":[33],"Unlike":[34],"previous":[35],"work":[36],"uses":[38,47],"local":[39],"image":[40],"features":[41],"at":[42,55],"fine":[43],"scales,":[44],"our":[45],"directly,":[49],"and":[50,113],"captures":[51],"their":[52],"high-order":[53],"correlations":[54],"coarse":[56],"scales":[57],"through":[58],"deep":[59],"multi-layer":[60],"neural":[61],"networks":[62,74],"restricted":[65],"Boltzmann":[66],"machines.":[67],"Specifically,":[68],"pretraining":[70],"stage":[71],"such":[73],"takes":[75],"role":[78],"feature":[80],"extraction.":[81],"Experimental":[82],"results":[83],"show":[84],"proposed":[87,104],"comparable":[90],"other":[92],"state-of-the-art":[93],"recognition":[94],"methods":[95],"in":[96],"terms":[97],"accuracy.":[99],"The":[100],"merits":[101],"come":[106],"from":[107],"simplicity":[109],"workflow":[112],"parallelizability":[115],"implementation":[118],"structure.":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}