{"id":"https://openalex.org/W4414170191","doi":"https://doi.org/10.1109/avss65446.2025.11149705","title":"Fine-Grained Video Indexing and Retrieval with Vision-Language Models","display_name":"Fine-Grained Video Indexing and Retrieval with Vision-Language Models","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4414170191","doi":"https://doi.org/10.1109/avss65446.2025.11149705"},"language":"en","primary_location":{"id":"doi:10.1109/avss65446.2025.11149705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","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/A5065092341","display_name":"Dong Gun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong Gun Park","raw_affiliation_strings":["Handong Global University,Pohang,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Handong Global University,Pohang,South Korea","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693317","display_name":"Soyeon Park","orcid":"https://orcid.org/0000-0003-4029-582X"},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Park","raw_affiliation_strings":["Handong Global University,Pohang,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Handong Global University,Pohang,South Korea","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731251","display_name":"Chang Ha Lee","orcid":"https://orcid.org/0000-0001-9411-3740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Ha Lee","raw_affiliation_strings":["GMDSOFT,Seongnam,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GMDSOFT,Seongnam,South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082431510","display_name":"Hyun-Kyoo Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunkyoo Choi","raw_affiliation_strings":["Korea Institute of Science and Technology Information,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information,Seoul,South Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069854677","display_name":"Charmgil Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Charmgil Hong","raw_affiliation_strings":["Handong Global University,Pohang,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Handong Global University,Pohang,South Korea","institution_ids":["https://openalex.org/I113825674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20138416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8187000155448914},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.6164000034332275},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5703999996185303},{"id":"https://openalex.org/keywords/smacker-video","display_name":"Smacker video","score":0.4731999933719635},{"id":"https://openalex.org/keywords/multimedia-information-retrieval","display_name":"Multimedia information retrieval","score":0.39410001039505005},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3431999981403351},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3312999904155731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472999930381775},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8187000155448914},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.586899995803833},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.4731999933719635},{"id":"https://openalex.org/C2776318140","wikidata":"https://www.wikidata.org/wiki/Q6934776","display_name":"Multimedia information retrieval","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.31380000710487366},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss65446.2025.11149705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","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":7,"referenced_works":["https://openalex.org/W2099736636","https://openalex.org/W2147069236","https://openalex.org/W2148972377","https://openalex.org/W4252076394","https://openalex.org/W4366330503","https://openalex.org/W4401023594","https://openalex.org/W4404340901"],"related_works":[],"abstract_inverted_index":{"The":[0,43,81],"exponential":[1],"growth":[2],"of":[3,67,77,94],"video":[4,17,27,61],"content":[5,51],"has":[6],"made":[7],"it":[8],"increasingly":[9],"difficult":[10],"to":[11,48,56,97],"locate":[12,98],"specific":[13],"information":[14],"within":[15],"large-scale":[16],"repositories.":[18],"To":[19,63],"address":[20],"this":[21],"challenge,":[22],"we":[23,71],"present":[24],"a":[25,39],"multimodal":[26],"indexing":[28],"framework":[29],"that":[30],"integrates":[31],"audio":[32],"transcription":[33],"and":[34,52,88,102],"visual":[35],"scene":[36],"analysis":[37],"into":[38],"unified,":[40],"searchable":[41],"structure.":[42],"system":[44,96],"uses":[45],"speech-to-text":[46],"models":[47,55],"transcribe":[49],"spoken":[50],"applies":[53],"vision-language":[54],"generate":[57],"semantic":[58],"descriptions":[59],"from":[60],"frames.":[62],"evaluate":[64],"the":[65,68,92,95],"effectiveness":[66],"proposed":[69],"framework,":[70],"conducted":[72],"experiments":[73],"on":[74],"174":[75],"hours":[76],"broadcast":[78],"television":[79],"content.":[80],"results,":[82],"which":[83],"include":[84],"both":[85],"retrieval":[86],"accuracy":[87],"query":[89],"latency,":[90],"confirm":[91],"ability":[93],"relevant":[99],"sections":[100],"efficiently":[101],"support":[103],"scalable":[104],"search":[105],"in":[106],"data-intensive":[107],"environments.":[108]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
