{"id":"https://openalex.org/W2565656701","doi":"https://doi.org/10.1109/cvpr.2017.347","title":"End-to-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering","display_name":"End-to-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2565656701","doi":"https://doi.org/10.1109/cvpr.2017.347","mag":"2565656701"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2017.347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101881857","display_name":"Youngjae Yu","orcid":"https://orcid.org/0000-0002-5867-0782"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjae Yu","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020828967","display_name":"Hyungjin Ko","orcid":"https://orcid.org/0000-0001-6564-733X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungjin Ko","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043029070","display_name":"Jongwook Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongwook Choi","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100664729","display_name":"Gunhee Kim","orcid":"https://orcid.org/0000-0002-9543-7453"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunhee Kim","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":7.8819,"has_fulltext":false,"cited_by_count":228,"citation_normalized_percentile":{"value":0.98069225,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3261","last_page":"3269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8845609426498413},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7606871128082275},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6690379977226257},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.669023871421814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6277535557746887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6003084778785706},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5780307054519653},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5406491160392761},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5236077904701233},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5049222111701965},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5040261149406433},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4875125586986542},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47295114398002625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39967024326324463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13665622472763062},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12363383173942566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845609426498413},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7606871128082275},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6690379977226257},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.669023871421814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6277535557746887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003084778785706},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5780307054519653},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5406491160392761},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5236077904701233},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5049222111701965},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5040261149406433},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4875125586986542},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47295114398002625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39967024326324463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13665622472763062},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12363383173942566},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2017.347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1514535095","https://openalex.org/W1521626219","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1893116441","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2131774270","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2153579005","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2295744208","https://openalex.org/W2302086703","https://openalex.org/W2526286384","https://openalex.org/W2536013558","https://openalex.org/W2584404671","https://openalex.org/W2914699769","https://openalex.org/W2963088515","https://openalex.org/W2963576560","https://openalex.org/W2963890755","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W4294170691","https://openalex.org/W4298033729","https://openalex.org/W6630875275","https://openalex.org/W6639622849","https://openalex.org/W6674330103","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6682691769","https://openalex.org/W6684090549","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,17,23,80],"high-level":[3],"concept":[4,26,90],"word":[5,38,58,97],"detector":[6,39,59],"that":[7,84,109],"can":[8],"be":[9],"integrated":[10],"with":[11,67,95],"any":[12,49,68],"video-to-language":[13,69,119],"models.":[14,35,70],"It":[15],"takes":[16],"video":[18],"as":[19,28],"input":[20],"and":[21,92,99,143],"generates":[22],"list":[24],"of":[25,117,128,137],"words":[27,91],"useful":[29],"semantic":[30,81],"priors":[31],"for":[32,53],"language":[33,103],"generation":[34],"The":[36],"proposed":[37,57,111],"has":[40,134],"two":[41],"important":[42],"properties.":[43],"First,":[44],"it":[45],"does":[46],"not":[47],"require":[48],"external":[50],"knowledge":[51],"sources":[52],"training.":[54],"Second,":[55],"the":[56,74,88,96,102,110,115,125],"is":[60],"trainable":[61],"in":[62,101,123],"an":[63],"end-to-end":[64],"manner":[65],"jointly":[66],"To":[71],"effectively":[72],"exploit":[73],"detected":[75,89],"words,":[76],"we":[77,121],"also":[78],"develop":[79],"attention":[82],"mechanism":[83],"selectively":[85],"focuses":[86],"on":[87],"fuse":[93],"them":[94],"encoding":[98],"decoding":[100],"model.":[104],"In":[105],"order":[106],"to":[107],"demonstrate":[108],"approach":[112,133],"indeed":[113],"improves":[114],"performance":[116],"multiple":[118],"tasks,":[120],"participate":[122],"all":[124],"four":[126],"tasks":[127],"LSMDC":[129],"2016":[130],"[18].":[131],"Our":[132],"won":[135],"three":[136],"them,":[138],"including":[139],"fill-in-the-blank,":[140],"multiple-choice":[141],"test,":[142],"movie":[144],"retrieval.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":6}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}