{"id":"https://openalex.org/W4309004600","doi":"https://doi.org/10.3390/bdcc6040136","title":"Improving Natural Language Person Description Search from Videos with Language Model Fine-Tuning and Approximate Nearest Neighbor","display_name":"Improving Natural Language Person Description Search from Videos with Language Model Fine-Tuning and Approximate Nearest Neighbor","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4309004600","doi":"https://doi.org/10.3390/bdcc6040136"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc6040136","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6040136","pdf_url":"https://www.mdpi.com/2504-2289/6/4/136/pdf?version=1668738776","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/6/4/136/pdf?version=1668738776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086542590","display_name":"Sumeth Yuenyong","orcid":"https://orcid.org/0000-0001-7774-0291"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Sumeth Yuenyong","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom 73170, Thailand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom 73170, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064821427","display_name":"Konlakorn Wongpatikaseree","orcid":"https://orcid.org/0000-0003-4444-1396"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Konlakorn Wongpatikaseree","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom 73170, Thailand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom 73170, Thailand","institution_ids":["https://openalex.org/I25399158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064821427","https://openalex.org/A5086542590"],"corresponding_institution_ids":["https://openalex.org/I25399158"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.2015,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48594804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"6","issue":"4","first_page":"136","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9990000128746033,"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":0.8507969975471497},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.752074122428894},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.636907696723938},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5438684821128845},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4877072274684906},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4790133833885193},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46773844957351685},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.462659627199173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4443660378456116},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4242638349533081},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37778568267822266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3441239595413208},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08112892508506775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507969975471497},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.752074122428894},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.636907696723938},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5438684821128845},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4877072274684906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4790133833885193},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46773844957351685},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.462659627199173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4443660378456116},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4242638349533081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37778568267822266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3441239595413208},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08112892508506775},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/bdcc6040136","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6040136","pdf_url":"https://www.mdpi.com/2504-2289/6/4/136/pdf?version=1668738776","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2e8e7869b1bd474791111d0e428649ab","is_oa":true,"landing_page_url":"https://doaj.org/article/2e8e7869b1bd474791111d0e428649ab","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 6, Iss 4, p 136 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-2289/6/4/136/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/bdcc6040136","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing; Volume 6; Issue 4; Pages: 136","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/bdcc6040136","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6040136","pdf_url":"https://www.mdpi.com/2504-2289/6/4/136/pdf?version=1668738776","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323439","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309004600.pdf","grobid_xml":"https://content.openalex.org/works/W4309004600.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2034365297","https://openalex.org/W2064675550","https://openalex.org/W2100799972","https://openalex.org/W2102605133","https://openalex.org/W2123024445","https://openalex.org/W2145065594","https://openalex.org/W2147800946","https://openalex.org/W2163922914","https://openalex.org/W2183341477","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2603203130","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2963037989","https://openalex.org/W2963365374","https://openalex.org/W2963449390","https://openalex.org/W2963469388","https://openalex.org/W2963882743","https://openalex.org/W2971355948","https://openalex.org/W2994983839","https://openalex.org/W2997421053","https://openalex.org/W3015686580","https://openalex.org/W3035390927","https://openalex.org/W3095440956","https://openalex.org/W3106250896","https://openalex.org/W3159683145","https://openalex.org/W3165835426","https://openalex.org/W4385245566","https://openalex.org/W6631637103","https://openalex.org/W6678470764","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W2132753198","https://openalex.org/W2369874856","https://openalex.org/W2182477562","https://openalex.org/W2792185758","https://openalex.org/W2787484455","https://openalex.org/W2119808169"],"abstract_inverted_index":{"Due":[0,131],"to":[1,27,32,106,127,132],"the":[2,51,79,87,96,111,133,154,174,177,188,195],"ubiquitous":[3],"nature":[4],"of":[5,16,50,95,99,135,176],"CCTV":[6],"cameras":[7],"that":[8,19,38,90,118,153,184],"record":[9],"continuously,":[10],"there":[11],"is":[12,31,45,54,63,117,156],"a":[13,35,40,65,92,121,145,162],"large":[14],"amount":[15],"video":[17,125],"data":[18,181],"are":[20],"unstructured.":[21],"Often,":[22],"when":[23,159],"these":[24],"recordings":[25],"have":[26],"be":[28,150,191],"reviewed,":[29],"it":[30],"look":[33],"for":[34],"specific":[36],"person":[37,60,100,146],"fits":[39],"certain":[41],"description.":[42],"Currently,":[43],"this":[44,69],"achieved":[46],"by":[47,82,194],"manual":[48],"inspection":[49],"videos,":[52],"which":[53],"both":[55],"time-consuming":[56],"and":[57,141,182],"labor-intensive.":[58],"While":[59],"description":[61,101,147],"search":[62,102,140,148],"not":[64],"new":[66,180],"topic,":[67],"in":[68,187],"work,":[70],"we":[71,76,119],"made":[72],"two":[73],"contributions.":[74],"First,":[75],"improve":[77],"upon":[78],"existing":[80],"state-of-the-art":[81],"proposing":[83],"unsupervised":[84],"finetuning":[85],"on":[86,110,161,179],"language":[88],"model":[89,143],"forms":[91],"main":[93],"part":[94],"text":[97],"branch":[98],"models.":[103],"This":[104],"led":[105],"higher":[107],"recall":[108],"values":[109],"standard":[112,163],"dataset.":[113],"The":[114],"second":[115],"contribution":[116],"engineered":[120],"complete":[122],"pipeline":[123],"from":[124],"files":[126],"fast":[128],"searchable":[129],"objects.":[130],"use":[134],"an":[136,169],"approximate":[137],"nearest":[138],"neighbor":[139],"some":[142],"optimizations,":[144],"can":[149,190],"performed":[151],"such":[152],"result":[155],"available":[157],"immediately":[158],"deployed":[160],"PC":[164],"with":[165],"no":[166],"GPU,":[167],"allowing":[168],"interactive":[170],"search.":[171,196],"We":[172],"demonstrated":[173],"effectiveness":[175],"system":[178],"showed":[183],"most":[185],"people":[186],"videos":[189],"successfully":[192],"discovered":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-11-20T00:00:00"}