{"id":"https://openalex.org/W4415708724","doi":"https://doi.org/10.1109/icme59968.2025.11209366","title":"A Zero Decoding Approach to Video Classification","display_name":"A Zero Decoding Approach to Video Classification","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708724","doi":"https://doi.org/10.1109/icme59968.2025.11209366"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5016038403","display_name":"Chen Ye Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Ye Gan","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103560215","display_name":"Jiangtao Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Wen","raw_affiliation_strings":["Research Institute,Shenzhen Tsinghua,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Research Institute,Shenzhen Tsinghua,Shenzhen,China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101944724","display_name":"Yuxing Han","orcid":"https://orcid.org/0000-0003-2558-8966"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Han","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016038403"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33929514,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9591000080108643,"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":0.9591000080108643,"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/T11309","display_name":"Music and Audio Processing","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/bitstream","display_name":"Bitstream","score":0.795799970626831},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6665999889373779},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5374000072479248},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5084999799728394},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.424699991941452},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3930000066757202},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.3862999975681305},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.37070000171661377},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.795799970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42640000581741333},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.424699991941452},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.3862999975681305},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C133529210","wikidata":"https://www.wikidata.org/wiki/Q1076113","display_name":"Scalable Video Coding","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.29490000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2833000123500824},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.27230000495910645},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":27,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W1993332189","https://openalex.org/W2008348094","https://openalex.org/W2016053056","https://openalex.org/W2016571104","https://openalex.org/W2024300411","https://openalex.org/W2030191558","https://openalex.org/W2050493487","https://openalex.org/W2118529802","https://openalex.org/W2194775991","https://openalex.org/W2551393996","https://openalex.org/W2555077524","https://openalex.org/W2755747701","https://openalex.org/W2799176631","https://openalex.org/W2892035503","https://openalex.org/W2918626955","https://openalex.org/W2963661130","https://openalex.org/W2963880930","https://openalex.org/W2988244882","https://openalex.org/W2990503944","https://openalex.org/W3136015878","https://openalex.org/W3138516171","https://openalex.org/W3173621652","https://openalex.org/W3194397797","https://openalex.org/W4214612132"],"related_works":[],"abstract_inverted_index":{"Classifying":[0],"videos":[1],"into":[2],"distinct":[3,88],"categories,":[4],"such":[5],"as":[6],"Sport":[7],"and":[8,16,35,40,85,95,104,132],"Music":[9],"Video,":[10],"is":[11],"crucial":[12],"for":[13,63,117],"multimedia":[14],"understanding":[15],"retrieval,":[17],"especially":[18],"with":[19],"growing":[20],"content":[21],"volume.":[22],"Traditional":[23],"methods":[24],"require":[25],"video":[26,56,80,134],"decompression":[27],"to":[28,57],"extract":[29],"pixel-level":[30],"features":[31],"like":[32],"color,":[33],"texture,":[34],"motion,":[36],"thereby":[37],"increasing":[38],"computational":[39],"storage":[41],"demands.":[42],"We":[43],"present":[44],"a":[45,55,72],"novel":[46],"approach":[47],"that":[48],"examines":[49],"only":[50],"the":[51,61],"compressed":[52],"bitstream":[53,64],"of":[54,130,140],"perform":[58],"classification,":[59],"eliminating":[60],"need":[62],"decoding.":[65],"To":[66],"validate":[67],"our":[68],"approach,":[69],"we":[70],"built":[71],"comprehensive":[73],"data":[74],"set":[75],"comprising":[76],"over":[77],"29,000":[78],"YouTube":[79],"clips,":[81],"totaling":[82],"6,000":[83],"hours":[84],"spanning":[86],"11":[87],"categories.":[89],"Our":[90],"evaluations":[91],"indicate":[92],"precision,":[93],"accuracy,":[94],"recall":[96],"rates":[97],"consistently":[98],"above":[99],"80%,":[100],"many":[101],"exceeding":[102],"90%,":[103],"some":[105],"reaching":[106],"99%.":[107],"The":[108],"algorithm":[109,126],"operates":[110],"approximately":[111],"15,000":[112],"times":[113],"faster":[114],"than":[115],"real-time":[116],"30fps":[118],"videos,":[119],"outperforming":[120],"traditional":[121],"Dynamic":[122],"Time":[123],"Warping":[124],"(DTW)":[125],"by":[127,137],"seven":[128],"orders":[129,139],"magnitude":[131],"state-of-the-art":[133],"classification":[135],"model":[136],"three":[138],"magnitude.":[141]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}
