{"id":"https://openalex.org/W4408345700","doi":"https://doi.org/10.1109/icassp49660.2025.10888493","title":"Enhancing Video-Text Matching via Sparse Stratified Sampling","display_name":"Enhancing Video-Text Matching via Sparse Stratified Sampling","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345700","doi":"https://doi.org/10.1109/icassp49660.2025.10888493"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888493","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":"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/A5043763521","display_name":"Chenyang Lyu","orcid":"https://orcid.org/0000-0002-3403-7050"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Lyu","raw_affiliation_strings":["Alibaba International Digital Commerce,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052375254","display_name":"Wenxi Li","orcid":"https://orcid.org/0000-0001-8449-0489"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Li","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071808662","display_name":"Tianbo Ji","orcid":"https://orcid.org/0000-0003-0143-6220"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianbo Ji","raw_affiliation_strings":["Nantong University,Nantong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nantong University,Nantong,China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071890018","display_name":"Liting Zhou","orcid":"https://orcid.org/0000-0002-7778-8743"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Liting Zhou","raw_affiliation_strings":["Dublin City University,Dublin,Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062730187","display_name":"Pintu Lohar","orcid":"https://orcid.org/0000-0002-5328-1585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pintu Lohar","raw_affiliation_strings":["Sitare University,Indore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sitare University,Indore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Hiroshima University,Hiroshima,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshima University,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088191810","display_name":"Longyue Wang","orcid":"https://orcid.org/0000-0002-9062-6183"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyue Wang","raw_affiliation_strings":["Alibaba International Digital Commerce,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02842362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9991000294685364,"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":0.9991000294685364,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9954000115394592,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.6914066076278687},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.5461243391036987},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5381361842155457},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4846852123737335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3938673734664917},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3148060441017151},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19951003789901733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1420874297618866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914066076278687},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.5461243391036987},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5381361842155457},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4846852123737335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3938673734664917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3148060441017151},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19951003789901733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1420874297618866},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888493","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":[{"score":0.46000000834465027,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1981377530","https://openalex.org/W2425121537","https://openalex.org/W2473169921","https://openalex.org/W2753311918","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2964213933","https://openalex.org/W2966683369","https://openalex.org/W2979826702","https://openalex.org/W2981582341","https://openalex.org/W2981851019","https://openalex.org/W2990153998","https://openalex.org/W2998166190","https://openalex.org/W3034730770","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3036007088","https://openalex.org/W3043840704","https://openalex.org/W3044495139","https://openalex.org/W3094502228","https://openalex.org/W3119243803","https://openalex.org/W3130796238","https://openalex.org/W3156636935","https://openalex.org/W3168640669","https://openalex.org/W3169472988","https://openalex.org/W3174873881","https://openalex.org/W3204588463","https://openalex.org/W3205408642","https://openalex.org/W4214604251","https://openalex.org/W4280651853","https://openalex.org/W4293795227","https://openalex.org/W4295135076","https://openalex.org/W4304098310","https://openalex.org/W4312380001","https://openalex.org/W4312763739","https://openalex.org/W4312962707","https://openalex.org/W4327644049","https://openalex.org/W4385572645","https://openalex.org/W4385572712","https://openalex.org/W4387969090","https://openalex.org/W4397026222","https://openalex.org/W4404965628","https://openalex.org/W4410659598","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6750041603","https://openalex.org/W6757817989","https://openalex.org/W6766582784","https://openalex.org/W6791353385","https://openalex.org/W6849307739"],"related_works":["https://openalex.org/W2387471420","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Video-text":[0],"matching":[1,44,193],"is":[2],"a":[3,32,65],"critical":[4],"task":[5],"in":[6,164,190],"multimedia":[7],"retrieval,":[8],"but":[9],"traditional":[10],"methods":[11],"often":[12],"fail":[13],"to":[14,24,72],"capture":[15],"the":[16,42,68,106,112,137],"diversity":[17],"and":[18,26,56,96,111,123,128,134,158,182],"depth":[19],"of":[20,85,139,153,177],"video":[21,48,76,109,126,165],"content":[22,49],"due":[23],"inefficient":[25],"inaccurate":[27],"frame":[28],"sampling.":[29],"We":[30,81],"propose":[31,82],"novel":[33],"sparse":[34,147],"stratified":[35,148],"sampling":[36,58,93,103,149],"technique":[37,150],"that":[38,91,100],"can":[39],"substantially":[40],"improve":[41],"video-text":[43,192],"process":[45],"by":[46],"segmenting":[47],"into":[50],"clusters":[51],"based":[52,104],"on":[53,105,119,156,160,180,184],"relevant":[54],"features":[55],"selectively":[57],"representative":[59],"frames.":[60],"Our":[61,146],"method":[62,141],"further":[63],"introduces":[64],"threshold":[66],"for":[67,125,162],"feature":[69],"metric":[70],"used":[71],"divide":[73],"clusters,":[74],"eliminating":[75],"frames":[77,110],"with":[78],"low":[79],"relevance.":[80],"two":[83],"variants":[84],"our":[86,140,172],"approach:":[87],"an":[88,97],"offline":[89],"approach":[90,99,173],"performs":[92],"before":[94],"training,":[95],"online":[98],"dynamically":[101],"conducts":[102],"relevance":[107],"between":[108],"text":[113],"query":[114],"during":[115],"training.":[116],"Extensive":[117],"experiments":[118],"datasets":[120],"like":[121],"MSRVTT":[122,157],"AVSD":[124,161],"retrieval":[127,166],"multiple-choice":[129,169],"VideoQA":[130,170],"datasets,":[131],"including":[132],"AVQA":[133,181],"Music-AVQA,":[135,185],"demonstrate":[136],"superiority":[138],"over":[142,154],"previous":[143],"state-of-the-art":[144],"approaches.":[145],"achieves":[151,174],"improvements":[152,176],"1.2%":[155],"1.7%":[159],"R@1":[163],"tasks.":[167],"For":[168],"tasks,":[171],"significant":[175],"1.8%":[178],"accuracy":[179],"3.9%":[183],"strongly":[186],"supporting":[187],"its":[188],"effectiveness":[189],"enhancing":[191],"systems.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}