{"id":"https://openalex.org/W3009149353","doi":"https://doi.org/10.1109/wacv45572.2020.9093344","title":"Domain-Specific Semantics Guided Approach to Video Captioning","display_name":"Domain-Specific Semantics Guided Approach to Video Captioning","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009149353","doi":"https://doi.org/10.1109/wacv45572.2020.9093344","mag":"3009149353"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5101542848","display_name":"M. Hemalatha","orcid":"https://orcid.org/0000-0003-1048-3846"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"M. Hemalatha","raw_affiliation_strings":["Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113563423","display_name":"C. Chandra Sekhar","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Chandra Sekhar","raw_affiliation_strings":["Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101542848"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":1.8563,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87594945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1576","last_page":"1585"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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":0.9980999827384949,"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/closed-captioning","display_name":"Closed captioning","score":0.918420672416687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8674560785293579},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6680307984352112},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6671351790428162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6293618083000183},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5773855447769165},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5139784216880798},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4719758927822113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43064746260643005},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42749708890914917},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36645135283470154},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3278834819793701},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1704464852809906}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.918420672416687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674560785293579},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6680307984352112},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6671351790428162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6293618083000183},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5773855447769165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5139784216880798},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4719758927822113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43064746260643005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42749708890914917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36645135283470154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3278834819793701},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1704464852809906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1686810756","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2012592962","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2164290393","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2527145521","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2584992898","https://openalex.org/W2607119937","https://openalex.org/W2608022654","https://openalex.org/W2608988379","https://openalex.org/W2618127004","https://openalex.org/W2786533745","https://openalex.org/W2808203533","https://openalex.org/W2887712318","https://openalex.org/W2889418103","https://openalex.org/W2897043747","https://openalex.org/W2913822893","https://openalex.org/W2948358897","https://openalex.org/W2962835968","https://openalex.org/W2962958773","https://openalex.org/W2963088515","https://openalex.org/W2963175879","https://openalex.org/W2963576560","https://openalex.org/W2963758027","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W3098682680","https://openalex.org/W6623995992","https://openalex.org/W6630875275","https://openalex.org/W6634426396","https://openalex.org/W6637373629","https://openalex.org/W6639432524","https://openalex.org/W6684090549","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2095030957","https://openalex.org/W2066827917"],"abstract_inverted_index":{"In":[0,33,46],"video":[1,7,16,37,54,73,94],"captioning,":[2],"the":[3,11,15,19,67,83,90,96,104,112,119,130,135,151,156,162],"description":[4],"of":[5,69,71,107,150,155,164],"a":[6,36,62,72],"usually":[8],"relies":[9],"on":[10,89,167],"domain":[12,63,113],"to":[13,22,53,65,75],"which":[14],"belongs.":[17],"Typically,":[18],"videos":[20],"belong":[21],"wide":[23],"range":[24],"domains":[25,87],"such":[26],"as":[27],"sports,":[28],"music,":[29],"news,":[30],"cooking,":[31],"etc.":[32],"many":[34],"cases,":[35],"can":[38],"be":[39],"associated":[40],"with":[41],"more":[42],"than":[43],"one":[44],"domain.":[45],"this":[47],"paper,":[48],"we":[49,81],"propose":[50],"an":[51],"approach":[52,128,158],"captioning":[55],"that":[56],"uses":[57,129],"domain-specific":[58,105,116,120],"decoders.":[59],"We":[60],"build":[61],"classifier":[64],"obtain":[66],"estimates":[68],"probabilities":[70],"belonging":[74],"different":[76],"domains.":[77],"For":[78],"each":[79],"video,":[80],"identify":[82],"top":[84],"-":[85],"k":[86],"based":[88],"estimated":[91],"probabilities.":[92],"Each":[93],"in":[95,102],"training":[97,103],"data":[98],"set":[99],"is":[100,159],"shared":[101],"decoders":[106,117],"top-k":[108],"labels":[109],"obtained":[110],"from":[111,138],"classifier.":[114],"The":[115,126,143,153],"use":[118],"semantic":[121],"tags":[122],"for":[123,133],"generating":[124],"captions.":[125],"proposed":[127,157],"Temporal":[131],"VLAD":[132],"preprocessing":[134],"features":[136,145],"extracted":[137],"2D-CNN":[139],"and":[140,173],"3D-CNN":[141],"features.":[142],"preprocessed":[144],"provide":[146],"better":[147],"feature":[148],"representation":[149],"videos.":[152],"effectiveness":[154],"demonstrated":[160],"through":[161],"results":[163],"experimental":[165],"studies":[166],"Microsoft":[168],"Video":[169],"Description":[170],"(MSVD)":[171],"corpus":[172],"MSR-VTT":[174],"dataset.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}