{"id":"https://openalex.org/W4408353008","doi":"https://doi.org/10.1109/icassp49660.2025.10887668","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","display_name":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353008","doi":"https://doi.org/10.1109/icassp49660.2025.10887668"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064282062","display_name":"Haochen Wang","orcid":"https://orcid.org/0000-0001-6272-7545"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochen Wang","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012388","display_name":"Kai Hu","orcid":"https://orcid.org/0000-0003-1436-9522"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangcai Gao","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9941999912261963,"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":0.9811000227928162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.727913498878479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6681278944015503},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5323669910430908},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3560470938682556}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.727913498878479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681278944015503},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5323669910430908},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3560470938682556}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2130237711","https://openalex.org/W2765716052","https://openalex.org/W2789028076","https://openalex.org/W2888302696","https://openalex.org/W2951161814","https://openalex.org/W2963323070","https://openalex.org/W2963890755","https://openalex.org/W2963963993","https://openalex.org/W2970062726","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3120043490","https://openalex.org/W3152574567","https://openalex.org/W3175961224","https://openalex.org/W3181186176","https://openalex.org/W3205961173","https://openalex.org/W4214922754","https://openalex.org/W4295101003","https://openalex.org/W4382202558","https://openalex.org/W4385572712","https://openalex.org/W4385990960","https://openalex.org/W4386071707","https://openalex.org/W4392909790","https://openalex.org/W4400033239","https://openalex.org/W4402671548","https://openalex.org/W4404784276","https://openalex.org/W6796581206","https://openalex.org/W6797235774"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"Remote":[0],"work":[1],"and":[2,31,59,71,101,109,148,190],"online":[3],"courses":[4],"have":[5],"become":[6],"important":[7],"methods":[8],"of":[9,17,87],"knowledge":[10],"dissemination,":[11],"leading":[12,165],"to":[13,41,56,152,166,192],"a":[14,84,116,133],"large":[15],"number":[16],"document-based":[18],"instructional":[19],"videos.":[20],"Unlike":[21],"traditional":[22],"video":[23,135,171],"datasets,":[24],"these":[25],"videos":[26,79],"mainly":[27],"feature":[28,142],"rich-text":[29],"images":[30],"audio":[32],"that":[33,180],"are":[34],"densely":[35],"packed":[36],"with":[37,83,95,144,162],"information":[38],"closely":[39],"tied":[40],"the":[42,68,74,122,158,176,188],"visual":[43],"content,":[44],"requiring":[45],"advanced":[46],"multimodal":[47],"understanding":[48],"capabilities.":[49,112],"However,":[50],"this":[51,64],"domain":[52],"remains":[53],"underexplored":[54],"due":[55],"dataset":[57,72,92,178,191],"availability":[58],"its":[60],"inherent":[61],"complexity.":[62],"In":[63],"paper,":[65],"we":[66,114,130],"introduce":[67],"DocVideoQA":[69,177],"task":[70],"for":[73,127],"first":[75],"time,":[76],"comprising":[77],"1,454":[78],"across":[80],"23":[81],"categories":[82],"total":[85],"duration":[86],"about":[88],"828":[89],"hours.":[90],"The":[91],"is":[93,160],"annotated":[94],"154K":[96],"question-answer":[97],"pairs":[98],"generated":[99],"manually":[100],"via":[102],"GPT,":[103],"assessing":[104],"models\u2019":[105],"comprehension,":[106],"temporal":[107],"awareness,":[108],"modality":[110,125,154],"integration":[111],"Initially,":[113],"establish":[115],"baseline":[117],"using":[118],"open-source":[119],"MLLMs.":[120],"Recognizing":[121],"challenges":[123],"in":[124,169],"comprehension":[126],"document-centric":[128,170],"videos,":[129],"present":[131],"DV-LLaMA,":[132],"robust":[134],"MLLM":[136],"baseline.":[137],"Our":[138],"method":[139],"enhances":[140],"unimodal":[141],"extraction":[143],"diverse":[145],"instruction-tuning":[146],"data":[147],"employs":[149],"contrastive":[150],"learning":[151],"strengthen":[153],"integration.":[155],"Through":[156],"fine-tuning,":[157],"LLM":[159],"equipped":[161],"audio-visual":[163],"capabilities,":[164],"significant":[167],"improvements":[168],"understanding.":[172],"Extensive":[173],"testing":[174],"on":[175],"shows":[179],"DV-LLaMA":[181],"significantly":[182],"outperforms":[183],"existing":[184],"models.":[185],"We\u2019ll":[186],"release":[187],"code":[189],"facilitate":[193],"future":[194],"research.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}