{"id":"https://openalex.org/W4399423097","doi":"https://doi.org/10.1145/3652583.3658061","title":"QAVidCap: Enhancing Video Captioning through Question Answering Techniques","display_name":"QAVidCap: Enhancing Video Captioning through Question Answering Techniques","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423097","doi":"https://doi.org/10.1145/3652583.3658061"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658061","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103275076","display_name":"Hui Li Liu","orcid":"https://orcid.org/0000-0002-3905-0668"},"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":true,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3905-0668","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029568096","display_name":"Xiaojun Wan","orcid":"https://orcid.org/0000-0001-6887-1994"},"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":"Xiaojun Wan","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6887-1994","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103275076"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.4762,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61367188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"164"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940999746322632,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9765999913215637,"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/closed-captioning","display_name":"Closed captioning","score":0.9872581362724304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8688844442367554},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7762267589569092},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6825445890426636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5694088935852051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5524609684944153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5318927764892578},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45643532276153564},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43094539642333984},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42262518405914307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32875311374664307},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12549719214439392}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9872581362724304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8688844442367554},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7762267589569092},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6825445890426636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694088935852051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5524609684944153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5318927764892578},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45643532276153564},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43094539642333984},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42262518405914307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32875311374664307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12549719214439392},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.4099999964237213,"display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423097.pdf","grobid_xml":"https://content.openalex.org/works/W4399423097.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2425121537","https://openalex.org/W2765716052","https://openalex.org/W2883910824","https://openalex.org/W2888442053","https://openalex.org/W2931018260","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2952132648","https://openalex.org/W2962762898","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963748441","https://openalex.org/W2963811641","https://openalex.org/W2963890755","https://openalex.org/W2963916161","https://openalex.org/W2964110616","https://openalex.org/W2964220823","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2996319563","https://openalex.org/W3034999214","https://openalex.org/W3035237998","https://openalex.org/W3035365026","https://openalex.org/W3127165192","https://openalex.org/W3166366124","https://openalex.org/W3174257385","https://openalex.org/W3175961224","https://openalex.org/W3187433838","https://openalex.org/W3197457832","https://openalex.org/W3204868383","https://openalex.org/W3205021045","https://openalex.org/W3213632785","https://openalex.org/W3214192224","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4214663214","https://openalex.org/W4287674181","https://openalex.org/W4312463400","https://openalex.org/W4382240304","https://openalex.org/W4385572712","https://openalex.org/W4385800837","https://openalex.org/W4385859649","https://openalex.org/W4386057717","https://openalex.org/W4386066385","https://openalex.org/W4389520402","https://openalex.org/W6782465632"],"related_works":["https://openalex.org/W2993670781","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W3113264705","https://openalex.org/W3009270862","https://openalex.org/W2099715052"],"abstract_inverted_index":{"Video":[0],"captioning":[1,67,85],"is":[2],"the":[3,47,99,141],"task":[4],"of":[5,143],"describing":[6,46],"video":[7,48,66,118],"content":[8],"using":[9],"natural":[10],"sentences.":[11],"While":[12],"recent":[13],"models":[14],"have":[15],"shown":[16],"significant":[17],"improvements":[18],"in":[19,42],"metrics,":[20],"there":[21],"are":[22],"still":[23],"some":[24],"unresolved":[25],"issues.":[26],"Model-generated":[27],"captions":[28,40],"often":[29],"contain":[30],"factual":[31],"errors":[32],"and":[33,44,78,116,130,137],"omit":[34],"important":[35],"details.":[36],"In":[37,50],"contrast,":[38],"human-written":[39,79],"excel":[41],"accurately":[43],"comprehensively":[45],"content.":[49],"this":[51],"work,":[52],"we":[53,93],"propose":[54,82],"a":[55,83,103],"novel":[56],"method":[57],"that":[58],"utilizes":[59],"question":[60],"answering":[61],"(QA)":[62],"techniques":[63],"to":[64,87,97,101],"enhance":[65],"models.":[68],"We":[69,81,120],"start":[70],"by":[71],"generating":[72],"QA":[73,90,104],"pairs":[74],"from":[75],"both":[76],"videos":[77],"captions.":[80,119],"QA-enhanced":[84],"model":[86,100,111],"better":[88],"leverage":[89],"information.":[91],"Finally,":[92],"employ":[94],"reinforcement":[95],"learning":[96],"train":[98],"maximize":[102],"reward.":[105],"By":[106],"incorporating":[107],"QA-related":[108],"techniques,":[109],"our":[110,144],"can":[112],"generate":[113],"more":[114],"accurate":[115],"comprehensive":[117],"conduct":[121],"experiments":[122],"on":[123],"three":[124],"datasets,":[125],"namely":[126],"ActivityNet":[127],"Captions,":[128],"YouCookII":[129],"MSR-VTT.":[131],"The":[132],"experimental":[133],"results,":[134],"ablation":[135],"studies":[136],"human":[138],"evaluations":[139],"demonstrate":[140],"advantages":[142],"method.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}