{"id":"https://openalex.org/W4406459611","doi":"https://doi.org/10.1109/bigdata62323.2024.10825179","title":"SparrowVQE: Visual Question Explanation for Course Content Understanding","display_name":"SparrowVQE: Visual Question Explanation for Course Content Understanding","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459611","doi":"https://doi.org/10.1109/bigdata62323.2024.10825179"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5100456941","display_name":"Jialu Li","orcid":"https://orcid.org/0000-0002-1296-4603"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialu Li","raw_affiliation_strings":["Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114656447","display_name":"Manish Kumar Thota","orcid":null},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Kumar Thota","raw_affiliation_strings":["Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114656448","display_name":"Ruslan Gokhman","orcid":null},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruslan Gokhman","raw_affiliation_strings":["Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114656449","display_name":"Radek Holik","orcid":null},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radek Holik","raw_affiliation_strings":["Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032593598","display_name":"Youshan Zhang","orcid":"https://orcid.org/0009-0004-5791-9971"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youshan Zhang","raw_affiliation_strings":["Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA","institution_ids":["https://openalex.org/I19772626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19772626"],"apc_list":null,"apc_paid":null,"fwci":0.2142,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54810162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1814","last_page":"1823"},"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9905999898910522,"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/course","display_name":"Course (navigation)","score":0.8502001762390137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328677535057068},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5421018004417419},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08851942420005798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08343875408172607}],"concepts":[{"id":"https://openalex.org/C2777552389","wikidata":"https://www.wikidata.org/wiki/Q1962728","display_name":"Course (navigation)","level":2,"score":0.8502001762390137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328677535057068},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5421018004417419},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08851942420005798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08343875408172607},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":62,"referenced_works":["https://openalex.org/W79621300","https://openalex.org/W125693051","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W1996418862","https://openalex.org/W2133512280","https://openalex.org/W2277195237","https://openalex.org/W2524168323","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2563399268","https://openalex.org/W2786356574","https://openalex.org/W2793429163","https://openalex.org/W2901466771","https://openalex.org/W2963518342","https://openalex.org/W3004037805","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3034594935","https://openalex.org/W3036601975","https://openalex.org/W3105232955","https://openalex.org/W3159433218","https://openalex.org/W3161465839","https://openalex.org/W3177797549","https://openalex.org/W3201068857","https://openalex.org/W3204666440","https://openalex.org/W4240244593","https://openalex.org/W4283731999","https://openalex.org/W4298392976","https://openalex.org/W4299527668","https://openalex.org/W4304192731","https://openalex.org/W4318718936","https://openalex.org/W4321487403","https://openalex.org/W4377192428","https://openalex.org/W4379520461","https://openalex.org/W4385571189","https://openalex.org/W4386655575","https://openalex.org/W4388647843","https://openalex.org/W4388727314","https://openalex.org/W4390437716","https://openalex.org/W4390465735","https://openalex.org/W4390873312","https://openalex.org/W4400435190","https://openalex.org/W4402727764","https://openalex.org/W6682086655","https://openalex.org/W6694395031","https://openalex.org/W6749743566","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6780218876","https://openalex.org/W6785642512","https://openalex.org/W6791353385","https://openalex.org/W6798231272","https://openalex.org/W6846178434","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6856529530","https://openalex.org/W6857162426","https://openalex.org/W6859375428","https://openalex.org/W6869883758","https://openalex.org/W6898505805","https://openalex.org/W6917636526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4318717247","https://openalex.org/W2267656092","https://openalex.org/W2317874921","https://openalex.org/W2736755255","https://openalex.org/W4362648715","https://openalex.org/W2009385780","https://openalex.org/W3082623308"],"abstract_inverted_index":{"Visual":[0,36],"Question":[1,37],"Answering":[2],"(VQA)":[3],"research":[4],"seeks":[5],"to":[6,10,30,46],"create":[7],"AI":[8],"systems":[9],"answer":[11],"natural":[12],"language":[13,163],"questions":[14],"in":[15,178,187],"images,":[16,82],"yet":[17],"VQA":[18,45,192],"methods":[19,186],"often":[20],"yield":[21],"overly":[22],"simplistic":[23],"and":[24,54,87,121,133,136,142,150,183],"short":[25],"answers.":[26],"This":[27],"paper":[28],"aims":[29],"advance":[31],"the":[32,42,56,128,155,161,188],"field":[33],"by":[34],"introducing":[35],"Explanation":[38],"(VQE),":[39],"which":[40],"enhances":[41],"ability":[43],"of":[44,85,116],"provide":[47],"detailed":[48],"explanations":[49],"rather":[50],"than":[51],"brief":[52],"responses":[53],"address":[55],"need":[57],"for":[58],"more":[59],"complex":[60],"interaction":[61],"with":[62,110,131,158,165],"visual":[63,152],"content.":[64],"We":[65,106],"first":[66],"created":[67],"an":[68,166],"MLVQE":[69,181],"dataset":[70,182],"from":[71],"a":[72,96,99,111],"14-week":[73],"streamed":[74],"video":[75],"machine":[76],"learning":[77],"course,":[78],"including":[79],"885":[80],"slide":[81,140],"110,407":[83],"words":[84],"transcripts,":[86],"9,416":[88],"designed":[89],"question-answer":[90],"(QA)":[91],"pairs.":[92],"Next,":[93],"we":[94],"proposed":[95],"novel":[97],"SparrowVQE,":[98],"small":[100],"3":[101],"billion":[102],"parameters":[103],"multimodal":[104,117],"model.":[105],"trained":[107],"our":[108,146,173,179],"model":[109,130,157,164],"three-stage":[112],"training":[113],"mechanism":[114],"consisting":[115],"pre-training":[118],"(slide":[119],"images":[120],"transcripts":[122,132,159],"feature":[123],"alignment),":[124],"instruction":[125],"tuning":[126],"(tuning":[127],"pre-trained":[129],"QA":[134,143],"pairs),":[135],"domain":[137],"fine-tuning":[138],"(fine-tuning":[139],"image":[141],"pairs).":[144],"Eventually,":[145],"SparrowVQE":[147,174],"can":[148],"understand":[149],"connect":[151],"information":[153],"using":[154,160],"SigLIP":[156],"Phi-2":[162],"MLP":[167],"adapter.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"that":[172],"achieves":[175],"better":[176],"performance":[177],"developed":[180],"outperforms":[184],"state-of-the-art":[185],"other":[189],"five":[190],"benchmark":[191],"datasets.":[193],"The":[194],"source":[195],"code":[196],"is":[197],"available":[198],"at":[199],"https://github.com/rrymn/SparrowVQE.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}