{"id":"https://openalex.org/W2622044949","doi":"https://doi.org/10.1007/s11263-017-1018-6","title":"Sentence Directed Video Object Codiscovery","display_name":"Sentence Directed Video Object Codiscovery","publication_year":2017,"publication_date":"2017-06-09","ids":{"openalex":"https://openalex.org/W2622044949","doi":"https://doi.org/10.1007/s11263-017-1018-6","mag":"2622044949"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-017-1018-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-017-1018-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-017-1018-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-017-1018-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009585935","display_name":"Haonan Yu","orcid":"https://orcid.org/0000-0001-9882-4929"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haonan Yu","raw_affiliation_strings":["Baidu Research - Institute of Deep Learning, Sunnyvale, CA, 94089, USA"],"raw_orcid":"https://orcid.org/0000-0001-9882-4929","affiliations":[{"raw_affiliation_string":"Baidu Research - Institute of Deep Learning, Sunnyvale, CA, 94089, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079140683","display_name":"Jeffrey Mark Siskind","orcid":"https://orcid.org/0000-0002-0105-6503"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Mark Siskind","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009585935"],"corresponding_institution_ids":[],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.4622,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.72439793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"124","issue":"3","first_page":"312","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/leverage","display_name":"Leverage (statistics)","score":0.7164877653121948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6989954113960266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6800821423530579},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6700289249420166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5672227144241333},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5102572441101074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4733854830265045},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4511227011680603},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.44872915744781494}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7164877653121948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6989954113960266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800821423530579},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6700289249420166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5672227144241333},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5102572441101074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4733854830265045},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4511227011680603},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.44872915744781494}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-017-1018-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-017-1018-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-017-1018-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-017-1018-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-017-1018-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-017-1018-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1305804611","display_name":null,"funder_award_id":"522954-IIS","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G6363158233","display_name":null,"funder_award_id":"W911NF-10-2-0060","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G7733068915","display_name":"NRI: Collaborative Research: RobotSLANG: Simultaneous Localization, Mapping, and Language Acquisition","funder_award_id":"1522954","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2622044949.pdf","grobid_xml":"https://content.openalex.org/works/W2622044949.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W38568571","https://openalex.org/W95926497","https://openalex.org/W210657420","https://openalex.org/W262578090","https://openalex.org/W411141150","https://openalex.org/W1502024436","https://openalex.org/W1536680647","https://openalex.org/W1545752326","https://openalex.org/W1559723967","https://openalex.org/W1566289585","https://openalex.org/W1572567476","https://openalex.org/W1584193343","https://openalex.org/W1585614163","https://openalex.org/W1596841185","https://openalex.org/W1686810756","https://openalex.org/W1727982597","https://openalex.org/W1755205674","https://openalex.org/W1773149199","https://openalex.org/W1934890906","https://openalex.org/W1966601141","https://openalex.org/W1973054923","https://openalex.org/W1991367009","https://openalex.org/W1995820507","https://openalex.org/W1996140089","https://openalex.org/W2002837010","https://openalex.org/W2010181071","https://openalex.org/W2016016818","https://openalex.org/W2019660985","https://openalex.org/W2020636921","https://openalex.org/W2048343491","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2086842362","https://openalex.org/W2101194540","https://openalex.org/W2104670258","https://openalex.org/W2107558380","https://openalex.org/W2110485445","https://openalex.org/W2117539524","https://openalex.org/W2118246710","https://openalex.org/W2121465811","https://openalex.org/W2126579184","https://openalex.org/W2128715914","https://openalex.org/W2133280805","https://openalex.org/W2136036867","https://openalex.org/W2136885855","https://openalex.org/W2137023887","https://openalex.org/W2142900973","https://openalex.org/W2146055337","https://openalex.org/W2148596671","https://openalex.org/W2151103935","https://openalex.org/W2156094048","https://openalex.org/W2156689847","https://openalex.org/W2158847908","https://openalex.org/W2161969291","https://openalex.org/W2163292664","https://openalex.org/W2337252826","https://openalex.org/W2467181293","https://openalex.org/W2520705252","https://openalex.org/W2950527759","https://openalex.org/W2962835968","https://openalex.org/W2963109634","https://openalex.org/W2963576560","https://openalex.org/W2963811219","https://openalex.org/W3021229333","https://openalex.org/W6633497868","https://openalex.org/W6635155997","https://openalex.org/W6679915538","https://openalex.org/W6683167905","https://openalex.org/W6684821475","https://openalex.org/W7006809620"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W1990856605","https://openalex.org/W3120436346"],"abstract_inverted_index":{"Video":[0],"object":[1,22,30,82,111,132,147,163],"codiscovery":[2,18],"can":[3,55,79,103],"leverage":[4],"the":[5,14,73,93,109,176],"weak":[6],"semantic":[7,94],"constraint":[8],"implied":[9],"by":[10,107,180],"sentences":[11],"that":[12,38,66],"describe":[13],"video":[15,90],"content.":[16],"Our":[17,165],"method,":[19],"like":[20],"other":[21],"codetection":[23],"techniques,":[24],"does":[25],"not":[26],"employ":[27],"any":[28],"pretrained":[29],"models":[31],"or":[32,58],"detectors.":[33],"Unlike":[34],"most":[35],"prior":[36],"work":[37],"focuses":[39],"on":[40,117,126,140,156,167],"codetecting":[41],"large":[42],"objects":[43,61],"which":[44],"are":[45],"usually":[46,98],"salient":[47],"both":[48],"in":[49],"size":[50],"and":[51,100,149],"appearance,":[52],"our":[53,77],"method":[54,78],"discover":[56],"small":[57],"medium":[59],"sized":[60],"as":[62,64],"well":[63],"ones":[65],"may":[67],"be":[68],"occluded":[69],"for":[70],"part":[71],"of":[72,84,124,138,143,154,159,170,175],"video.":[74],"More":[75],"importantly,":[76],"codiscover":[80],"multiple":[81],"instances":[83],"different":[85],"classes":[86],"within":[87],"a":[88,127,141,157],"single":[89],"clip.":[91],"Although":[92],"information":[95],"employed":[96],"is":[97],"simple":[99],"weak,":[101],"it":[102],"greatly":[104],"boost":[105],"performance":[106],"constraining":[108],"hypothesized":[110],"locations.":[112],"Experiments":[113],"show":[114],"promising":[115],"results":[116],"three":[118],"datasets:":[119],"an":[120,134,150],"average":[121,135,151],"IoU":[122,136,152],"score":[123,137,153],"0.423":[125],"new":[128],"dataset":[129],"with":[130,145,161],"15":[131],"classes,":[133,148],"0.373":[139],"subset":[142,158,169],"CAD-120":[144],"5":[146],"0.358":[155],"MPII-Cooking":[160,171],"7":[162],"classes.":[164],"result":[166],"this":[168],"improves":[172],"upon":[173],"those":[174],"previous":[177],"state-of-the-art":[178],"methods":[179],"significant":[181],"margins.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}