{"id":"https://openalex.org/W4389374124","doi":"https://doi.org/10.1145/3628797.3629011","title":"Enhancing Video Retrieval with Robust CLIP-Based Multimodal System","display_name":"Enhancing Video Retrieval with Robust CLIP-Based Multimodal System","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389374124","doi":"https://doi.org/10.1145/3628797.3629011"},"language":"en","primary_location":{"id":"doi:10.1145/3628797.3629011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3629011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","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/A5093428979","display_name":"Minh-Dung Le-Quynh","orcid":"https://orcid.org/0009-0004-0972-4109"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minh-Dung Le-Quynh","raw_affiliation_strings":["Lazada Vietnam, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Lazada Vietnam, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078983799","display_name":"Anh-Tuan Nguyen","orcid":"https://orcid.org/0009-0004-8382-1206"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Anh-Tuan Nguyen","raw_affiliation_strings":["University of Science, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Science, Viet Nam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093428980","display_name":"Anh-Tuan Quang-Hoang","orcid":"https://orcid.org/0009-0006-0209-9288"},"institutions":[{"id":"https://openalex.org/I1292974536","display_name":"Ford Motor Company (United States)","ror":"https://ror.org/00g2tkw06","country_code":"US","type":"company","lineage":["https://openalex.org/I1292974536"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anh-Tuan Quang-Hoang","raw_affiliation_strings":["Ford Motor, United States"],"affiliations":[{"raw_affiliation_string":"Ford Motor, United States","institution_ids":["https://openalex.org/I1292974536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019762266","display_name":"Van-Huy Dinh","orcid":"https://orcid.org/0009-0004-1374-5236"},"institutions":[{"id":"https://openalex.org/I4387155935","display_name":"HUTECH University","ror":"https://ror.org/05xpj2n48","country_code":null,"type":"education","lineage":["https://openalex.org/I4387155935"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van-Huy Dinh","raw_affiliation_strings":["HUTECH University, Viet Nam"],"affiliations":[{"raw_affiliation_string":"HUTECH University, Viet Nam","institution_ids":["https://openalex.org/I4387155935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031473482","display_name":"Tien-Huy Nguyen","orcid":"https://orcid.org/0009-0000-0196-6083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien-Huy Nguyen","raw_affiliation_strings":["University of Information Technology, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102901293","display_name":"Hoang-Bach Ngo","orcid":"https://orcid.org/0009-0002-2290-1187"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoang-Bach Ngo","raw_affiliation_strings":["University of Science, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Science, Viet Nam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010685866","display_name":"Minh-Hung An","orcid":"https://orcid.org/0009-0001-0394-4731"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Hung An","raw_affiliation_strings":["FPT Telecom, Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT Telecom, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5093428979"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.681,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86720096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"972","last_page":"979"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9955000281333923,"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":0.8873482942581177},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.698587954044342},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6328865885734558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5490071773529053},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5152614116668701},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4972563087940216},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.48426100611686707},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4497353136539459},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36893177032470703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2466401755809784},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11997324228286743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8873482942581177},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.698587954044342},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6328865885734558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5490071773529053},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5152614116668701},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4972563087940216},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.48426100611686707},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4497353136539459},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36893177032470703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2466401755809784},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11997324228286743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628797.3629011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3629011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2059304719","https://openalex.org/W2065506310","https://openalex.org/W2293499654","https://openalex.org/W2511925527","https://openalex.org/W2603445054","https://openalex.org/W2885402090","https://openalex.org/W2970231061","https://openalex.org/W2973481893","https://openalex.org/W2998702515","https://openalex.org/W3034068260","https://openalex.org/W3034603197","https://openalex.org/W3135367836","https://openalex.org/W3187371978","https://openalex.org/W4213378403","https://openalex.org/W4312759111"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W1494563618","https://openalex.org/W2176457742","https://openalex.org/W2185495922"],"abstract_inverted_index":{"In":[0],"the":[1,8,59,68,71,83,116],"rapidly":[2],"evolving":[3],"landscape":[4],"of":[5,120],"multimedia":[6],"data,":[7,114],"need":[9],"for":[10,78],"efficient":[11],"content-based":[12,121],"video":[13,27,37,107,122],"retrieval":[14,28,56],"has":[15],"become":[16],"increasingly":[17],"vital.":[18],"To":[19],"tackle":[20],"this":[21],"challenge,":[22],"we":[23],"introduce":[24],"an":[25],"interactive":[26],"system":[29,69],"designed":[30],"to":[31,45,96],"retrieve":[32],"data":[33],"from":[34],"vast":[35],"online":[36],"collections":[38],"efficiently.":[39],"Our":[40,90],"solution":[41],"encompasses":[42],"rich":[43],"textual":[44,88],"visual":[46,86],"descriptions,":[47],"advanced":[48],"human":[49],"detection":[50],"capabilities,":[51],"and":[52,63,87,109,111,118],"a":[53],"novel":[54],"Sketch-Text":[55],"mechanism,":[57],"rendering":[58],"search":[60],"process":[61],"comprehensive":[62],"precise.":[64],"At":[65],"its":[66,79],"core,":[67],"leverages":[70],"Contrastive":[72],"Language-Image":[73],"Pretraining":[74],"(CLIP)":[75],"model,":[76],"renowned":[77],"proficiency":[80],"in":[81],"bridging":[82],"gap":[84],"between":[85],"data.":[89],"user-friendly":[91],"web":[92],"application":[93],"allows":[94],"users":[95],"create":[97],"queries,":[98],"explore":[99],"top":[100],"results,":[101],"find":[102],"similar":[103],"images,":[104],"preview":[105],"short":[106],"clips,":[108],"select":[110],"export":[112],"pertinent":[113],"enhancing":[115],"effectiveness":[117],"accessibility":[119],"retrieval.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
