{"id":"https://openalex.org/W4392970297","doi":"https://doi.org/10.1109/tbc.2024.3434520","title":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","display_name":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4392970297","doi":"https://doi.org/10.1109/tbc.2024.3434520"},"language":"en","primary_location":{"id":"doi:10.1109/tbc.2024.3434520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2024.3434520","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"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 Broadcasting","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.11694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuoyuan Li","orcid":"https://orcid.org/0009-0003-7370-4068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Li","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-7370-4068","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114137703","display_name":"Zikun Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikun Yuan","raw_affiliation_strings":["Information Security and National Computing Grid Laboratory, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0006-2822-1093","affiliations":[{"raw_affiliation_string":"Information Security and National Computing Grid Laboratory, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7163-6263"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7163-6263","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407381","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0001-9100-2906"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9100-2906","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohu Tang","orcid":"https://orcid.org/0000-0002-7938-7812"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu Tang","raw_affiliation_strings":["Information Security and National Computing Grid Laboratory, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-7938-7812","affiliations":[{"raw_affiliation_string":"Information Security and National Computing Grid Laboratory, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":null,"display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7266-5579","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8669,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96547175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"70","issue":"4","first_page":"1236","last_page":"1253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9975000023841858,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9975000023841858,"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":0.9947999715805054,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7101748585700989},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6497042775154114},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5840290784835815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5681277513504028},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42310625314712524},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41839566826820374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06528100371360779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101748585700989},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6497042775154114},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5840290784835815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681277513504028},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42310625314712524},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41839566826820374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06528100371360779},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tbc.2024.3434520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2024.3434520","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"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 Broadcasting","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.11694","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.11694","pdf_url":"https://arxiv.org/pdf/2403.11694","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.11694","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.11694","pdf_url":"https://arxiv.org/pdf/2403.11694","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6241311946","display_name":null,"funder_award_id":"WK3490000006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392970297.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1969665649","https://openalex.org/W1974698526","https://openalex.org/W2005003004","https://openalex.org/W2011734484","https://openalex.org/W2016938946","https://openalex.org/W2100220302","https://openalex.org/W2108931344","https://openalex.org/W2120478155","https://openalex.org/W2126509046","https://openalex.org/W2126897420","https://openalex.org/W2132747369","https://openalex.org/W2140199336","https://openalex.org/W2145023731","https://openalex.org/W2146395539","https://openalex.org/W2167584295","https://openalex.org/W2189153151","https://openalex.org/W2470139095","https://openalex.org/W2590077255","https://openalex.org/W2610826476","https://openalex.org/W2778917380","https://openalex.org/W2792551103","https://openalex.org/W2889658408","https://openalex.org/W2889986507","https://openalex.org/W2939527329","https://openalex.org/W2963150697","https://openalex.org/W2964343881","https://openalex.org/W2989676862","https://openalex.org/W2990205821","https://openalex.org/W3108395087","https://openalex.org/W3109810474","https://openalex.org/W3117707016","https://openalex.org/W3132455321","https://openalex.org/W3152708635","https://openalex.org/W3153323090","https://openalex.org/W3168057692","https://openalex.org/W3168354393","https://openalex.org/W3182236906","https://openalex.org/W3186764622","https://openalex.org/W3188610266","https://openalex.org/W3202918664","https://openalex.org/W3214224847","https://openalex.org/W4205700951","https://openalex.org/W4211162678","https://openalex.org/W4247047653","https://openalex.org/W4288325606","https://openalex.org/W4316660006","https://openalex.org/W4362655025","https://openalex.org/W4390873799","https://openalex.org/W4390874575","https://openalex.org/W6735925877","https://openalex.org/W6796524941","https://openalex.org/W6846581650","https://openalex.org/W6852629184"],"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],"modern":[1],"video":[2],"coding":[3],"standards,":[4],"block-based":[5],"inter":[6,85],"prediction":[7,86,144],"is":[8,109,136,149,166,194],"widely":[9],"adopted,":[10],"which":[11],"brings":[12],"high":[13],"compression":[14],"efficiency.":[15],"However,":[16],"in":[17,30,51,91,168],"natural":[18],"videos,":[19],"there":[20],"are":[21,35,95],"usually":[22],"multiple":[23],"moving":[24],"objects":[25,90],"of":[26,123,157,184],"arbitrary":[27],"shapes,":[28],"resulting":[29],"complex":[31],"motion":[32,134,155,174,182],"fields":[33],"that":[34,207],"difficult":[36],"to":[37,67,115,152,179,213],"represent":[38],"compactly.":[39],"This":[40],"problem":[41],"has":[42],"been":[43],"tackled":[44],"by":[45,97],"more":[46,60,64,160,189],"flexible":[47,61],"block":[48],"partitioning":[49],"methods":[50],"the":[52,59,92,105,112,116,120,131,154,163,169,181,197,208,230],"Versatile":[53],"Video":[54],"Coding":[55],"(VVC)":[56],"standard,":[57],"but":[58],"partitions":[62],"require":[63],"overhead":[65],"bits":[66],"signal":[68],"and":[69,176,187,217,235],"still":[70],"cannot":[71],"be":[72],"made":[73],"arbitrarily":[74],"shaped.":[75],"To":[76],"address":[77],"this":[78],"limitation,":[79],"we":[80],"propose":[81],"an":[82],"object":[83,106],"segmentation-assisted":[84],"method":[87,193,210],"(SAIP),":[88],"where":[89],"reference":[93,113,199],"frames":[94],"segmented":[96],"some":[98],"advanced":[99],"technologies.":[100],"With":[101],"a":[102],"proper":[103],"indication,":[104],"segmentation":[107,132,147,164],"mask":[108,148,165],"translated":[110],"from":[111],"frame":[114,118],"current":[117],"as":[119],"arbitrary-shaped":[121],"partition":[122,177,188],"different":[124,140,158,185],"regions":[125,159,186],"without":[126],"any":[127],"extra":[128],"signal.":[129],"Using":[130],"mask,":[133],"compensation":[135],"separately":[137],"performed":[138],"for":[139,173,225],"regions,":[141],"achieving":[142],"higher":[143],"accuracy.":[145],"The":[146,191],"further":[150],"used":[151],"code":[153],"vectors":[156],"efficiently.":[161],"Moreover,":[162],"considered":[167],"joint":[170],"rate-distortion":[171],"optimization":[172],"estimation":[175,178],"derive":[180],"vector":[183],"accurately.":[190],"proposed":[192,209],"implemented":[195],"into":[196],"VVC":[198],"software,":[200],"VTM":[201],"version":[202],"12.0.":[203],"Experimental":[204],"results":[205],"show":[206],"achieves":[211],"up":[212],"1.98%,":[214],"1.14%,":[215],"0.79%,":[216],"on":[218],"average":[219],"0.82%,":[220],"0.49%,":[221],"0.37%":[222],"BD-rate":[223],"reduction":[224],"common":[226],"test":[227],"sequences,":[228],"under":[229],"Low-delay":[231,233],"P,":[232],"B,":[234],"Random":[236],"Access":[237],"configurations,":[238],"respectively.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
