{"id":"https://openalex.org/W4392909574","doi":"https://doi.org/10.1109/icassp48485.2024.10447533","title":"Adaptive Secondary Transform Sets for Video Coding Beyond AV1","display_name":"Adaptive Secondary Transform Sets for Video Coding Beyond AV1","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909574","doi":"https://doi.org/10.1109/icassp48485.2024.10447533"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447533","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5044217760","display_name":"Yushin Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yushin Cho","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,California,USA","Tencent Media Lab, Palo Alto, California, USA"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,California,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, California, USA","institution_ids":["https://openalex.org/I70745867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082511351","display_name":"Madhu Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madhu Krishnan","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,California,USA","Tencent Media Lab, Palo Alto, California, USA"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,California,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, California, USA","institution_ids":["https://openalex.org/I70745867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572557","display_name":"Xin Zhao","orcid":"https://orcid.org/0000-0002-7103-7666"},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,California,USA","Tencent Media Lab, Palo Alto, California, USA"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,California,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, California, USA","institution_ids":["https://openalex.org/I70745867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449791","display_name":"Shan Liu","orcid":"https://orcid.org/0000-0003-1847-8769"},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Liu","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,California,USA","Tencent Media Lab, Palo Alto, California, USA"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,California,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, California, USA","institution_ids":["https://openalex.org/I70745867"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044217760"],"corresponding_institution_ids":["https://openalex.org/I70745867"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02761069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4100","last_page":"4104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9995999932289124,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9995999932289124,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9972000122070312,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.644706666469574},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.587031364440918},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35208365321159363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34459763765335083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2314993441104889},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14968669414520264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644706666469574},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.587031364440918},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35208365321159363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34459763765335083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2314993441104889},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14968669414520264}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447533","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":4,"referenced_works":["https://openalex.org/W2140199336","https://openalex.org/W3089462661","https://openalex.org/W3168057692","https://openalex.org/W3202918664"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,33],"this":[1],"paper,":[2],"a":[3,61],"research":[4,144],"progress":[5],"on":[6],"applying":[7],"adaptive":[8],"secondary":[9,45,57],"transform":[10,46,58,63,89],"set":[11,47,64],"in":[12,114],"the":[13,34,52,55,68,71,76,79,84,98,104,150],"context":[14],"of":[15,25,38,54,86,133,143],"ongoing":[16],"next-generation":[17],"video":[18,106],"coding":[19,107,111],"standardization":[20],"beyond":[21],"AV1":[22],"(namely":[23],"AV2)":[24],"AOM":[26,134],"(Alliance":[27],"for":[28,128,149],"Open":[29],"Media)":[30],"is":[31,48,65,81],"presented.":[32],"current":[35],"reference":[36],"software":[37,142],"AV2,":[39],"namely":[40],"AVM":[41,141],"(AOM":[42],"Video":[43],"Model),":[44],"chosen":[49],"mode-dependently":[50],"and":[51,118,125,154,159],"index":[53],"selected":[56],"kernel":[59],"within":[60],"given":[62],"signaled":[66],"into":[67],"bitstream":[69],"with":[70,83,140],"minimum":[72],"bit":[73],"cost.":[74],"With":[75],"proposed":[77,99],"method,":[78],"encoder":[80],"empowered":[82],"capability":[85],"selecting":[87],"any":[88],"sets":[90],"from":[91],"multiple":[92],"candidates.":[93],"Experiment":[94],"results":[95],"demonstrate":[96],"that":[97],"method":[100],"contributes":[101],"to":[102],"improving":[103],"overall":[105],"efficiency.":[108],"The":[109],"average":[110],"gains":[112,148],"measured":[113],"weighted":[115],"YUV":[116],"PSNR":[117],"SSIM":[119],"BD-Rates":[120],"are":[121,156],"observed":[122],"as":[123],"0.20%":[124],"0.62%":[126],"respectively":[127],"All":[129],"Intra":[130],"(AI)":[131],"configuration":[132],"CTC":[135],"(Common":[136],"Test":[137],"Condition)":[138],"v4":[139],"anchor":[145],"v4.":[146],"Coding":[147],"higher":[151],"resolutions":[152],"4K":[153],"2K":[155],"larger,":[157],"0.29%":[158],"0.23%":[160],"respectively.":[161]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}