{"id":"https://openalex.org/W4414229127","doi":"https://doi.org/10.1109/tcsvt.2025.3609803","title":"APSam: An Aggregating-Then-Pruning Sampler for Question-Conditional Denoising","display_name":"APSam: An Aggregating-Then-Pruning Sampler for Question-Conditional Denoising","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4414229127","doi":"https://doi.org/10.1109/tcsvt.2025.3609803"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3609803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3609803","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5102617130","display_name":"Jiafeng Liang","orcid":"https://orcid.org/0000-0002-5747-6187"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiafeng Liang","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111079844","display_name":"Shixin Jiang","orcid":"https://orcid.org/0009-0005-9685-9243"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixin Jiang","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459385","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0003-3414-2421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":["State Grid Anhui Electric Power Research Institute, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Grid Anhui Electric Power Research Institute, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387149","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0002-4937-6784"},"institutions":[{"id":"https://openalex.org/I3087508612","display_name":"Pride Foundation","ror":"https://ror.org/05tewmz75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3087508612"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["resides, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"resides, Shanghai, China","institution_ids":["https://openalex.org/I3087508612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114767850","display_name":"Zekun Wang","orcid":"https://orcid.org/0000-0002-6708-6844"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun Wang","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112939449","display_name":"Xiaowei Mao","orcid":"https://orcid.org/0009-0001-7163-9560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Mao","raw_affiliation_strings":["State Grid Anhui Electric Power Research Institute, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Grid Anhui Electric Power Research Institute, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579974","display_name":"Kai Lv","orcid":"https://orcid.org/0000-0002-7942-3115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Lv","raw_affiliation_strings":["State Grid Anhui Electric Power Research Institute, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Grid Anhui Electric Power Research Institute, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347769","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-1846-6445"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017671620","display_name":"Bing Qin","orcid":"https://orcid.org/0000-0002-2543-5604"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102617130"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12695752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"1754","last_page":"1765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.8925999999046326,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.8925999999046326,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.8884000182151794,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.8834999799728394,"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/semantics","display_name":"Semantics (computer science)","score":0.5891000032424927},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5619000196456909},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5412999987602234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5343000292778015},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.531000018119812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4970000088214874},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.49390000104904175},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42179998755455017},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4154999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616100013256073},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5619000196456909},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4059999883174896},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.2542000114917755},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3609803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3609803","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1283684484","display_name":null,"funder_award_id":"A003","funder_id":"https://openalex.org/F4320330373","funder_display_name":"Research and Innovation in Science and Technology Project"},{"id":"https://openalex.org/G2219353148","display_name":null,"funder_award_id":"62276083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4442529403","display_name":null,"funder_award_id":"U22B2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330373","display_name":"Research and Innovation in Science and Technology Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2150593711","https://openalex.org/W2735159761","https://openalex.org/W2883429621","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2963524571","https://openalex.org/W2964067226","https://openalex.org/W2964220823","https://openalex.org/W2997591391","https://openalex.org/W2998166190","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3159630763","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3187433838","https://openalex.org/W3197457832","https://openalex.org/W4283801188","https://openalex.org/W4285283873","https://openalex.org/W4312849330","https://openalex.org/W4312864639","https://openalex.org/W4312974690","https://openalex.org/W4313071966","https://openalex.org/W4313163028","https://openalex.org/W4319300272","https://openalex.org/W4377235294","https://openalex.org/W4381233075","https://openalex.org/W4385567055","https://openalex.org/W4385567126","https://openalex.org/W4385572645","https://openalex.org/W4385681696","https://openalex.org/W4385767947","https://openalex.org/W4386071468","https://openalex.org/W4386076661","https://openalex.org/W4386902900","https://openalex.org/W4387969346","https://openalex.org/W4389519526","https://openalex.org/W4390872366","https://openalex.org/W4399399458","https://openalex.org/W4401069990","https://openalex.org/W4402727142","https://openalex.org/W4403182266","https://openalex.org/W4404035255","https://openalex.org/W4404782290","https://openalex.org/W4405429615","https://openalex.org/W4406171217","https://openalex.org/W4407949554","https://openalex.org/W4413146669"],"related_works":[],"abstract_inverted_index":{"Video":[0],"question":[1,86],"answering":[2],"(VideoQA)":[3],"necessitates":[4],"simultaneous":[5],"understanding":[6],"of":[7,16,23,63,77,81],"visual":[8,64,82,118],"and":[9,20,38,46,79,101,164,177],"linguistic":[10],"information,":[11],"requiring":[12],"both":[13],"in-depth":[14],"analysis":[15],"individual":[17],"modality":[18],"features":[19,78],"the":[21,43,67,71,74,143,170],"establishment":[22],"cross-modal":[24],"correlations":[25],"to":[26,42,115],"achieve":[27],"precise":[28],"reasoning.":[29],"However,":[30],"VideoQA":[31,157],"models":[32],"often":[33],"struggle":[34],"with":[35],"irrelevant":[36],"temporal":[37],"spatial":[39],"noise":[40,56,134],"due":[41],"dense":[44],"events":[45],"concepts":[47],"in":[48,73],"real-world":[49],"complex":[50,156],"video":[51],"contents.":[52],"Previous":[53],"works":[54],"reduce":[55],"by":[57,120,142],"only":[58],"sampling":[59],"a":[60,105,111,128,137],"fixed":[61],"number":[62],"tokens":[65,135],"at":[66],"patch":[68],"level,":[69],"overlooking":[70],"variation":[72],"required":[75],"granularities":[76,100],"quantities":[80],"cues":[83],"across":[84],"different":[85],"conditions.":[87],"To":[88],"address":[89],"these,":[90],"we":[91,109,126],"propose":[92,110,127],"an":[93],"Aggregating-then-Pruning":[94],"Sampler":[95],"(APSam),":[96],"which":[97,132],"diversifies":[98],"feature":[99],"adaptively":[102],"denoises":[103],"on":[104,153],"per-question":[106],"basis.":[107],"Specifically,":[108],"conditional":[112,129],"token":[113,130],"aggregator":[114],"obtain":[116],"multi-granularity":[117],"semantics":[119],"merging":[121],"similar":[122],"question-relevant":[123],"tokens.":[124],"Then,":[125],"pruner,":[131],"restricts":[133],"through":[136],"variable-capacity":[138],"receptive":[139],"field":[140],"determined":[141],"inputs.":[144],"Experimental":[145],"results":[146],"show":[147],"that":[148,169],"APSam":[149,171],"achieves":[150],"significant":[151],"performance":[152],"three":[154],"challenging":[155],"datasets,":[158],"<italic":[159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e.</i>,":[161],"AGQAv2,":[162],"NExT-QA,":[163],"STAR.":[165],"Further":[166],"analyses":[167],"reveal":[168],"also":[172],"exhibits":[173],"high":[174],"reasoning":[175],"capability":[176],"interpretability.":[178]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}