{"id":"https://openalex.org/W4409763692","doi":"https://doi.org/10.1109/csicc65765.2025.10967455","title":"Adaptive Chunking for VideoRAG Pipelines with a Newly Gathered Bilingual Educational Dataset","display_name":"Adaptive Chunking for VideoRAG Pipelines with a Newly Gathered Bilingual Educational Dataset","publication_year":2025,"publication_date":"2025-02-05","ids":{"openalex":"https://openalex.org/W4409763692","doi":"https://doi.org/10.1109/csicc65765.2025.10967455"},"language":"en","primary_location":{"id":"doi:10.1109/csicc65765.2025.10967455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc65765.2025.10967455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 29th International Computer Conference, Computer Society of Iran (CSICC)","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/A5084472484","display_name":"A. Askari Hemmat","orcid":"https://orcid.org/0000-0001-9673-4196"},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Arshia Hemmat","raw_affiliation_strings":["University of Isfahan,dept. Computer Engineering,Isfahan,Iran"],"affiliations":[{"raw_affiliation_string":"University of Isfahan,dept. Computer Engineering,Isfahan,Iran","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114654079","display_name":"Kianoosh Vadaei","orcid":null},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Kianoosh Vadaei","raw_affiliation_strings":["University of Isfahan,dept. Computer Engineering,Isfahan,Iran"],"affiliations":[{"raw_affiliation_string":"University of Isfahan,dept. Computer Engineering,Isfahan,Iran","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117292493","display_name":"Melika Shirian","orcid":null},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Melika Shirian","raw_affiliation_strings":["University of Isfahan,dept. Computer Engineering,Isfahan,Iran"],"affiliations":[{"raw_affiliation_string":"University of Isfahan,dept. Computer Engineering,Isfahan,Iran","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074418418","display_name":"Mohammad Heydari","orcid":"https://orcid.org/0000-0001-6764-4394"},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Hassan Heydari","raw_affiliation_strings":["University of Isfahan,dept. Computer Engineering,Isfahan,Iran"],"affiliations":[{"raw_affiliation_string":"University of Isfahan,dept. Computer Engineering,Isfahan,Iran","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049514148","display_name":"Afsaneh Fatemi","orcid":"https://orcid.org/0000-0003-1184-5917"},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Afsaneh Fatemi","raw_affiliation_strings":["University of Isfahan,dept. Computer Engineering,Isfahan,Iran"],"affiliations":[{"raw_affiliation_string":"University of Isfahan,dept. Computer Engineering,Isfahan,Iran","institution_ids":["https://openalex.org/I39268498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084472484"],"corresponding_institution_ids":["https://openalex.org/I39268498"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88957036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.8309999704360962,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.8309999704360962,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.8258000016212463,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.7867000102996826,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.8326656222343445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925812363624573},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6280753016471863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4558391273021698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3990420699119568},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32118383049964905},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16878801584243774}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8326656222343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925812363624573},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6280753016471863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4558391273021698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3990420699119568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32118383049964905},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16878801584243774},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csicc65765.2025.10967455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc65765.2025.10967455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 29th International Computer Conference, Computer Society of Iran (CSICC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4394972198","https://openalex.org/W4401453783","https://openalex.org/W4402916904","https://openalex.org/W4407951492","https://openalex.org/W4407952008","https://openalex.org/W6873370543"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4245487161","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"This":[0,57,175],"paper":[1],"introduces":[2],"an":[3,19],"innovative":[4],"approach":[5,134],"to":[6,91,96,114],"Retrieval-Augmented":[7],"Generation":[8],"(RAG)":[9],"for":[10,73,181,192],"video":[11,47,106,137,182],"question":[12],"answering":[13],"(VideoQA)":[14],"through":[15],"the":[16,24,60,123,158,164,169,186],"development":[17],"of":[18,26,62,68,125,171,188],"adaptive":[20,33],"chunking":[21,34,133],"methodology":[22,58],"and":[23,40,70,88,102,121,151,196],"creation":[25],"a":[27,83,178],"bilingual":[28,84],"educational":[29,51,193],"dataset.":[30],"Our":[31],"proposed":[32],"technique,":[35],"powered":[36],"by":[37,49],"CLIP":[38],"embeddings":[39],"SSIM":[41],"scores,":[42],"identifies":[43],"meaningful":[44],"transitions":[45],"in":[46],"content":[48,194],"segmenting":[50],"videos":[52],"into":[53],"semantically":[54],"coherent":[55],"chunks.":[56],"optimizes":[59],"processing":[61],"slide-based":[63],"lectures,":[64],"ensuring":[65],"efficient":[66],"integration":[67],"visual":[69],"textual":[71],"modalities":[72],"downstream":[74],"RAG":[75,183],"tasks.":[76],"To":[77],"support":[78],"this":[79],"work,":[80],"we":[81],"gathered":[82],"dataset":[85,202],"comprising":[86],"Persian":[87],"English":[89],"mid-":[90],"long-duration":[92],"academic":[93],"videos,":[94],"curated":[95],"reflect":[97],"diverse":[98],"topics,":[99],"teaching":[100],"styles,":[101],"multilingual":[103],"content.":[104],"Each":[105],"is":[107,203],"enriched":[108],"with":[109],"synthetic":[110],"question-answer":[111],"pairs":[112],"designed":[113],"challenge":[115],"pure":[116],"large":[117],"language":[118],"models":[119],"(LLMs)":[120],"underscore":[122],"necessity":[124],"retrieval-augmented":[126],"systems.":[127],"The":[128],"evaluation":[129],"compares":[130],"our":[131,154],"CLIP-SSIM-based":[132],"against":[135],"conventional":[136],"slicing":[138],"methods,":[139],"demonstrating":[140],"significant":[141],"improvements":[142],"across":[143],"RAGAS":[144],"metrics,":[145],"including":[146],"Answer":[147],"Relevance,":[148,150],"Context":[149],"Faithfulness.":[152],"Fur-thermore,":[153],"findings":[155],"reveal":[156],"that":[157],"multimodal":[159,189],"image-text":[160],"retrieval":[161],"scenario":[162],"achieves":[163],"best":[165],"overall":[166],"performance,":[167],"emphasizing":[168],"importance":[170],"integrating":[172],"complementary":[173],"modalities.":[174],"research":[176],"establishes":[177],"robust":[179],"framework":[180],"pipelines,":[184],"expanding":[185],"capabilities":[187],"AI":[190],"systems":[191],"analysis":[195],"retrieval<sup":[197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198,200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>The":[201],"publicly":[204],"available":[205],"at:":[206],"https://huggingface.co/datasets/uIAICIEduViQA.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}