{"id":"https://openalex.org/W2107905723","doi":"https://doi.org/10.1145/1386352.1386407","title":"A discrete direct retrieval model for image and video retrieval","display_name":"A discrete direct retrieval model for image and video retrieval","publication_year":2008,"publication_date":"2008-07-07","ids":{"openalex":"https://openalex.org/W2107905723","doi":"https://doi.org/10.1145/1386352.1386407","mag":"2107905723"},"language":"en","primary_location":{"id":"doi:10.1145/1386352.1386407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1386352.1386407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 international conference on Content-based image and video retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/r_manmatha/38/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109910347","display_name":"Shaolei Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaolei Feng","raw_affiliation_strings":["Siemens Corporate Research, Inc., Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055459215","display_name":"R. Manmatha","orcid":"https://orcid.org/0000-0003-2315-8583"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Manmatha","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.55,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9325915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"436"},"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":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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10824","display_name":"Image Retrieval and Classification 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":0.9945999979972839,"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":0.8079540729522705},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7088075280189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.660841703414917},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6541604399681091},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5769339799880981},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5699949860572815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5113529562950134},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4651986062526703},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.46163272857666016},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45762571692466736},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4534398317337036},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.44222503900527954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10283833742141724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079540729522705},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7088075280189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660841703414917},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6541604399681091},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5769339799880981},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5699949860572815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5113529562950134},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4651986062526703},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.46163272857666016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45762571692466736},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4534398317337036},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.44222503900527954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10283833742141724},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1386352.1386407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1386352.1386407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 international conference on Content-based image and video retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:r_manmatha-1075","is_oa":true,"landing_page_url":"https://works.bepress.com/r_manmatha/38","pdf_url":"https://works.bepress.com/r_manmatha/38/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R. Manmatha","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1029.2796","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1029.2796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://works.bepress.com/r_manmatha/38/download/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.5231","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.5231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir-publications.cs.umass.edu/pdf/MM-670.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:r_manmatha-1075","is_oa":true,"landing_page_url":"https://works.bepress.com/r_manmatha/38","pdf_url":"https://works.bepress.com/r_manmatha/38/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R. Manmatha","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107905723.pdf","grobid_xml":"https://content.openalex.org/works/W2107905723.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1484654248","https://openalex.org/W1544067897","https://openalex.org/W1599860700","https://openalex.org/W1651266332","https://openalex.org/W1666447063","https://openalex.org/W1792188165","https://openalex.org/W1934863104","https://openalex.org/W1971987737","https://openalex.org/W2000636201","https://openalex.org/W2020842694","https://openalex.org/W2070740689","https://openalex.org/W2096047541","https://openalex.org/W2114447088","https://openalex.org/W2125238156","https://openalex.org/W2127411609","https://openalex.org/W2128017662","https://openalex.org/W2128197086","https://openalex.org/W2128594317","https://openalex.org/W2129664360","https://openalex.org/W2137918516","https://openalex.org/W2141159588","https://openalex.org/W2141362318","https://openalex.org/W2150692003","https://openalex.org/W2156336347","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2123147980","https://openalex.org/W2066590080","https://openalex.org/W2076842684","https://openalex.org/W2918350319","https://openalex.org/W1539573266","https://openalex.org/W4387423606","https://openalex.org/W2513891871","https://openalex.org/W2187873862","https://openalex.org/W3101846449","https://openalex.org/W2086291077"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,34,59,63,120,155,174],"formal":[4],"framework":[5],"for":[6,102],"image":[7,118],"and":[8,141,154,163],"video":[9,142],"retrieval":[10,143,191],"using":[11,33],"discrete":[12,35],"Markov":[13],"random":[14],"fields":[15],"(MRF).":[16],"The":[17,29,104,168],"training":[18,47],"dataset":[19,153],"consists":[20],"of":[21,37,56,62,65,116,160],"images":[22,110,162],"with":[23],"keywords":[24],"(regions":[25],"are":[26,125,145],"not":[27],"labeled).":[28],"model":[30,95,105,133,179],"is":[31,51,68,83,134],"built":[32],"vocabulary":[36,61,177],"vector":[38],"quantized":[39],"region":[40],"or":[41],"point":[42],"features":[43],"generated":[44,75],"from":[45],"the":[46,54,57,113,178,194],"images.":[48],"Since":[49],"performance":[50,192],"dependent":[52],"on":[53,147,173,183],"size":[55],"vocabulary,":[58],"large":[60,71,175,186],"couple":[64],"million":[66],"visterms":[67],"used.":[69],"Such":[70],"vocabularies":[72],"cannot":[73],"be":[74],"by":[76,127,136],"conventional":[77],"clustering":[78],"algorithms":[79],"so":[80],"hierarchical":[81],"k-means":[82],"used":[84],"to":[85,112,193],"generate":[86],"it.":[87],"Unlike":[88],"many":[89],"previous":[90],"techniques,":[91],"our":[92],"MRF":[93],"based":[94,172],"doesn't":[96],"require":[97],"an":[98,117],"explicit":[99],"annotation":[100],"step":[101],"retrieval.":[103],"directly":[106],"ranks":[107],"all":[108],"test":[109],"according":[111],"posterior":[114],"probability":[115],"given":[119],"query.":[121],"Traditionally,":[122],"most":[123],"models":[124],"trained":[126,135],"maximizing":[128,137],"likelihood":[129],"-":[130],"instead":[131],"this":[132],"average":[138],"precision.":[139],"Image":[140],"experiments":[144],"performed":[146],"two":[148],"standard":[149],"datasets":[150,187],"(a":[151],"Corel":[152],"TRECVID3":[156],"dataset)":[157],"which":[158],"consist":[159],"4,500":[161],"about":[164],"44,100":[165],"keyframes":[166],"respectively.":[167],"results":[169],"show":[170],"that":[171],"visual":[176],"runs":[180],"extremely":[181],"fast":[182],"even":[184],"very":[185],"while":[188],"having":[189],"comparable":[190],"best":[195],"performing":[196],"(continuous":[197],"feature)":[198],"models.":[199]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}