{"id":"https://openalex.org/W2943294985","doi":"https://doi.org/10.1145/3297280.3297303","title":"Visual content based video retrieval on natural language queries","display_name":"Visual content based video retrieval on natural language queries","publication_year":2019,"publication_date":"2019-04-08","ids":{"openalex":"https://openalex.org/W2943294985","doi":"https://doi.org/10.1145/3297280.3297303","mag":"2943294985"},"language":"en","primary_location":{"id":"doi:10.1145/3297280.3297303","doi":"https://doi.org/10.1145/3297280.3297303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297280.3297303","pdf_url":null,"source":{"id":"https://openalex.org/S4306417581","display_name":"ACM Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"volume":null,"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":null,"display_name":"Ravi Bansal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravi Bansal","raw_affiliation_strings":["Google India Pvt. Ltd, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google India Pvt. Ltd, Bengaluru, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001115038","display_name":"Sandip Chakraborty","orcid":"https://orcid.org/0000-0003-3531-968X","observed_orcids":["https://orcid.org/0000-0003-3531-968X"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandip Chakraborty","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4003,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.67914252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5015000104904175,"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/T11439","display_name":"Video Analysis and Summarization","score":0.5015000104904175,"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":0.28220000863075256,"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":0.1281999945640564,"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/content-based-video-retrieval","display_name":"content-based video retrieval","score":0.8669999837875366},{"id":"https://openalex.org/keywords/natural-language-questions","display_name":"natural language queries","score":0.902999997138977},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/sentence-embeddings","display_name":"sentence embeddings","score":0.6869999766349792},{"id":"https://openalex.org/keywords/shared-embedding-space","display_name":"shared embedding space","score":0.7020000219345093},{"id":"https://openalex.org/keywords/neighborhood-constraints","display_name":"neighborhood constraints","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8573187589645386},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6285349726676941},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.574068546295166},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5737845301628113},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.5516234636306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476825833320618},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5030538439750671},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49855589866638184},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49051207304000854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4806738793849945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41182494163513184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22235843539237976},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12359604239463806},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297280.3297303","doi":"https://doi.org/10.1145/3297280.3297303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297280.3297303","pdf_url":null,"source":{"id":"https://openalex.org/S4306417581","display_name":"ACM Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W877909479","https://openalex.org/W1581862991","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1897761818","https://openalex.org/W1902237438","https://openalex.org/W2000220837","https://openalex.org/W2099736636","https://openalex.org/W2111092656","https://openalex.org/W2112429522","https://openalex.org/W2123301721","https://openalex.org/W2124033848","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2150510224","https://openalex.org/W2164290393","https://openalex.org/W2271840356","https://openalex.org/W2490414731","https://openalex.org/W2530794863","https://openalex.org/W2556388456","https://openalex.org/W2600463316","https://openalex.org/W2726631140","https://openalex.org/W2949117887","https://openalex.org/W2949335953","https://openalex.org/W2950276680","https://openalex.org/W2950635152","https://openalex.org/W2963389687","https://openalex.org/W2963758027","https://openalex.org/W2963843052","https://openalex.org/W3102887392"],"related_works":["https://openalex.org/W2490414731","https://openalex.org/W3013937728","https://openalex.org/W2981785383","https://openalex.org/W3017078581","https://openalex.org/W2111092656","https://openalex.org/W2965458216","https://openalex.org/W3036846062","https://openalex.org/W2741214001","https://openalex.org/W2394681831","https://openalex.org/W3158926"],"abstract_inverted_index":{"With":[0],"the":[1,36,100,121],"emergence":[2],"of":[3,8,35,40,59,91,107,125],"video-sharing":[4],"websites":[5],"uploading":[6],"thousands":[7],"videos":[9,41,60,126],"per":[10],"day,":[11],"content":[12,25],"based":[13,26,87],"video":[14,27,95,162],"retrieval":[15,28,58,165],"has":[16],"become":[17],"an":[18],"important":[19],"research":[20],"challenge.":[21],"Existing":[22],"approaches":[23],"for":[24,56,145,161],"lag":[29],"robustness":[30],"and":[31,38,42,61,75,127,141,163],"efficiency":[32],"in":[33,45,67,148,166],"terms":[34],"dynamics":[37],"variations":[39],"queries":[43],"expressed":[44],"natural":[46,68],"language.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,98,113],"develop":[52,81],"a":[53,82,104,115,138],"novel":[54],"approach":[55],"bi-directional":[57],"its":[62,131],"descriptions,":[63],"represented":[64],"through":[65],"sentences":[66,129],"language,":[69],"by":[70],"combining":[71],"various":[72,169],"state-of-the-art":[73],"learning":[74,106],"video/sentence":[76],"representation":[77],"techniques.":[78],"We":[79],"first":[80],"base":[83,101],"model":[84,102],"which":[85],"is":[86,135],"on":[88],"sentence":[89,164],"embedding":[90,109,123,150],"captions":[92],"generated":[93],"from":[94],"content.":[96],"Further":[97],"extend":[99],"with":[103,154,168],"joint":[105,149],"latent":[108],"space":[110,124],"model,":[111],"where":[112],"use":[114],"two-branch":[116],"neural":[117],"network":[118,134],"to":[119],"learn":[120],"shared":[122],"corresponding":[128],"expressing":[130],"description.":[132],"The":[133],"trained":[136],"using":[137],"maximum-margin":[139],"loss":[140],"uses":[142],"neighborhood":[143],"information":[144],"structure-preserving":[146],"constraints":[147],"space.":[151],"Our":[152],"experiments":[153],"three":[155],"different":[156],"datasets":[157],"show":[158],"promising":[159],"results":[160],"comparison":[167],"baseline":[170],"models.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-05-09T00:00:00"}