{"id":"https://openalex.org/W2164860686","doi":"https://doi.org/10.1109/cvpr.2010.5540118","title":"Towards semantic embedding in visual vocabulary","display_name":"Towards semantic embedding in visual vocabulary","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2164860686","doi":"https://doi.org/10.1109/cvpr.2010.5540118","mag":"2164860686"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2010.5540118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","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/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"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"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Harbin Institute of Technology, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023274785","display_name":"Hongxun Yao","orcid":"https://orcid.org/0000-0003-3298-2574"},"institutions":[{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]},{"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":"Hongxun Yao","raw_affiliation_strings":["Harbin Institute of Technology, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"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"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Harbin Institute of Technology, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"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"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Harbin Institute of Technology, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018478553","display_name":"Wen Gao","orcid":"https://orcid.org/0000-0002-8070-802X"},"institutions":[{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]},{"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"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Gao","raw_affiliation_strings":["Harbin Institute of Technology, Heilongjiang, China","Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Heilongjiang, China","institution_ids":["https://openalex.org/I4210161462","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016080094"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"],"apc_list":null,"apc_paid":null,"fwci":8.7284,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98240913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"918","last_page":"925"},"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":0.9990000128746033,"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":0.9958999752998352,"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":0.7748162746429443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6830469369888306},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.5335769057273865},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5163235068321228},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5079494118690491},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45432060956954956},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4346752464771271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4247701168060303},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4231767952442169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.416939914226532},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.3740383982658386},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.33005690574645996},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19682860374450684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748162746429443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6830469369888306},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.5335769057273865},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5163235068321228},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5079494118690491},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45432060956954956},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4346752464771271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4247701168060303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4231767952442169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.416939914226532},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3740383982658386},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.33005690574645996},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19682860374450684},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2010.5540118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.180.6031","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.6031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vilab.hit.edu.cn/%7Errji/index_files/CVPR10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1543983856","https://openalex.org/W1553150669","https://openalex.org/W1556531089","https://openalex.org/W1592774159","https://openalex.org/W1666447063","https://openalex.org/W1679913846","https://openalex.org/W2020999234","https://openalex.org/W2038721957","https://openalex.org/W2104170135","https://openalex.org/W2106097867","https://openalex.org/W2107034620","https://openalex.org/W2112020727","https://openalex.org/W2115755015","https://openalex.org/W2125574651","https://openalex.org/W2128017662","https://openalex.org/W2128638419","https://openalex.org/W2134446283","https://openalex.org/W2139956879","https://openalex.org/W2141303268","https://openalex.org/W2141362318","https://openalex.org/W2141465109","https://openalex.org/W2142120379","https://openalex.org/W2151103935","https://openalex.org/W2154490791","https://openalex.org/W2160225842","https://openalex.org/W2164877691","https://openalex.org/W2164996087","https://openalex.org/W2165846633","https://openalex.org/W2953139536","https://openalex.org/W2994982620","https://openalex.org/W4235505822","https://openalex.org/W6632664038","https://openalex.org/W6633472159","https://openalex.org/W6635368981","https://openalex.org/W6637249095","https://openalex.org/W6637308636","https://openalex.org/W6675679986","https://openalex.org/W6678757208","https://openalex.org/W6680735885","https://openalex.org/W6683014609","https://openalex.org/W6683732952","https://openalex.org/W6683978607","https://openalex.org/W6684290682","https://openalex.org/W6771369255","https://openalex.org/W7075742223"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2374066281","https://openalex.org/W2947282851","https://openalex.org/W3043037362","https://openalex.org/W4239790437","https://openalex.org/W2776636962"],"abstract_inverted_index":{"Visual":[0],"vocabulary":[1,26,65],"serves":[2],"as":[3,13,93,109,125],"a":[4,52,71,110,169],"fundamental":[5],"component":[6],"in":[7,43,133,154],"many":[8],"computer":[9,157],"vision":[10,158],"tasks,":[11],"such":[12],"object":[14],"recognition,":[15],"visual":[16,25,30,45,89,99],"search,":[17],"and":[18,139],"scene":[19],"modeling.":[20],"While":[21],"state-of-the-art":[22],"approaches":[23],"build":[24],"based":[27],"solely":[28],"on":[29,168,176],"statistics":[31],"of":[32],"local":[33],"image":[34,38,166],"patches,":[35],"the":[36,118,130,134,177],"correlative":[37],"labels":[39,62,106],"are":[40,91,107],"left":[41],"unexploited":[42],"generating":[44],"words.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"present":[51],"semantic":[53,58],"embedding":[54],"framework":[55],"to":[56,77,85,101,117,162],"integrate":[57],"information":[59],"from":[60,147],"Flickr":[61,170],"for":[63],"supervised":[64,140],"construction.":[66],"Our":[67],"main":[68],"contribution":[69],"is":[70],"Hidden":[72,111,135],"Markov":[73,131],"Random":[74],"Field":[75,120],"modeling":[76],"supervise":[78],"feature":[79,103],"space":[80],"quantization,":[81],"with":[82,121,160],"specialized":[83],"considerations":[84],"label":[86],"correlations:":[87],"Local":[88],"features":[90],"modeled":[92,108],"an":[94],"Observed":[95,119],"Field,":[96,112,136],"which":[97,113],"follows":[98],"metrics":[100],"partition":[102],"space.":[104],"Semantic":[105],"imposes":[114],"generative":[115],"supervision":[116],"WordNet-based":[122],"correlation":[123],"constraints":[124],"Gibbs":[126],"distribution.":[127],"By":[128],"simplifying":[129],"property":[132],"both":[137],"unsupervised":[138],"(label":[141],"independent)":[142],"vocabularies":[143],"can":[144],"be":[145],"derived":[146],"our":[148,152],"framework.":[149],"We":[150],"validate":[151],"performances":[153],"two":[155],"challenging":[156],"tasks":[159],"comparisons":[161],"state-of-the-arts:":[163],"(1)":[164],"Large-scale":[165],"search":[167],"60,000":[171],"database;":[172],"(2)":[173],"Object":[174],"recognition":[175],"PASCAL":[178],"VOC":[179],"database.":[180]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}