{"id":"https://openalex.org/W4417073310","doi":"https://doi.org/10.1145/3743093.3771054","title":"Dual-Branch Feature Modeling and Multi-Directional Motion Perception for Video Compression","display_name":"Dual-Branch Feature Modeling and Multi-Directional Motion Perception for Video Compression","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073310","doi":"https://doi.org/10.1145/3743093.3771054"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771054","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603417","display_name":"Zhi Liu","orcid":"https://orcid.org/0000-0001-7205-441X"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhi Liu","raw_affiliation_strings":["North China University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7205-441X","affiliations":[{"raw_affiliation_string":"North China University of Technology, Beijing, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yangbing Wang","orcid":"https://orcid.org/0009-0000-2715-4446"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangbing Wang","raw_affiliation_strings":["North China University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2715-4446","affiliations":[{"raw_affiliation_string":"North China University of Technology, Beijing, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan Li","orcid":"https://orcid.org/0009-0004-6535-8350"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["North China University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6535-8350","affiliations":[{"raw_affiliation_string":"North China University of Technology, Beijing, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023474030","display_name":"Hongyuan Jing","orcid":"https://orcid.org/0000-0002-5613-1216"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyuan Jing","raw_affiliation_strings":["Beijing Union University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5613-1216","affiliations":[{"raw_affiliation_string":"Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mengmeng Zhang","orcid":"https://orcid.org/0009-0000-7792-5878"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Zhang","raw_affiliation_strings":["Beijing Union University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7792-5878","affiliations":[{"raw_affiliation_string":"Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100603417"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38067257,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.5468999743461609,"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":0.5468999743461609,"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":0.3425000011920929,"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":0.05209999904036522,"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/codec","display_name":"Codec","score":0.5997999906539917},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.57669997215271},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5110999941825867},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.5037999749183655},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4207000136375427},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.39980000257492065},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3828999996185303},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3743000030517578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7378000020980835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6424000263214111},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2799000144004822},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.27140000462532043},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.26499998569488525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G180867268","display_name":null,"funder_award_id":"62473055","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073310.pdf","grobid_xml":"https://content.openalex.org/works/W4417073310.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2511458122","https://openalex.org/W2548527721","https://openalex.org/W2601564443","https://openalex.org/W2769654144","https://openalex.org/W2884585870","https://openalex.org/W2963420686","https://openalex.org/W2969260367","https://openalex.org/W3031546776","https://openalex.org/W3113521585","https://openalex.org/W3173272744","https://openalex.org/W3200120316","https://openalex.org/W4285483958","https://openalex.org/W4297965133","https://openalex.org/W4304087061","https://openalex.org/W4308235958","https://openalex.org/W4309591648","https://openalex.org/W4312774595","https://openalex.org/W4313058111","https://openalex.org/W4313291310","https://openalex.org/W4386065808","https://openalex.org/W4386598363","https://openalex.org/W4390479170","https://openalex.org/W4390659444","https://openalex.org/W4390990495","https://openalex.org/W4391092744","https://openalex.org/W4391288589","https://openalex.org/W4391365622","https://openalex.org/W4392908893","https://openalex.org/W4395038433","https://openalex.org/W4395691450","https://openalex.org/W4401567493","https://openalex.org/W4402772372"],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"deep":[1,152],"video":[2,37,153],"compression":[3,154],"in":[4,137],"the":[5,95,118,177],"feature":[6,16,33,58,97],"space":[7],"has":[8],"become":[9],"a":[10,24,45,54,103,157,171],"key":[11],"research":[12],"direction,":[13],"where":[14],"effective":[15],"modeling":[17,34,98],"is":[18,134],"essential.":[19],"However,":[20],"existing":[21],"methods":[22],"adopt":[23],"single-branch":[25],"architecture,":[26],"making":[27],"it":[28],"difficult":[29],"to":[30,115,162],"effectively":[31,87],"perform":[32],"on":[35,77],"complex":[36,124],"frames.":[38],"To":[39],"address":[40],"this":[41],"issue,":[42],"we":[43,101],"propose":[44],"Context":[46],"and":[47,69,81,112,121,150,169],"Fine-grained":[48,65],"Fusion":[49,74],"Module":[50,107],"(CFFM),":[51],"which":[52,109],"adopts":[53],"dual-branch":[55],"architecture":[56],"for":[57],"modeling.":[59],"Each":[60],"branch":[61],"consists":[62],"of":[63],"two":[64,70],"Spatial":[66],"Aggregation":[67],"Modules":[68],"Dilated":[71],"Contextual":[72],"Residual":[73],"Modules,":[75],"focusing":[76],"local":[78],"fine-grained":[79],"details":[80],"global":[82],"contextual":[83],"information,":[84],"respectively.":[85],"By":[86],"capturing":[88],"these":[89],"complementary":[90],"features,":[91],"CFFM":[92],"significantly":[93],"enhances":[94],"overall":[96],"capability.":[99],"Additionally,":[100],"introduce":[102],"Multi-Directional":[104],"Motion":[105],"Perception":[106],"(MDMP),":[108],"integrates":[110],"multi-directional":[111],"standard":[113],"convolutions":[114],"dynamically":[116],"expand":[117],"receptive":[119],"field":[120],"adaptively":[122],"model":[123],"motion":[125,128],"patterns,":[126],"improving":[127],"offset":[129],"estimation.":[130],"The":[131],"entire":[132],"framework":[133],"jointly":[135],"optimized":[136],"an":[138],"end-to-end":[139],"manner.":[140],"Experimental":[141],"results":[142],"show":[143],"that":[144],"our":[145],"method":[146],"outperforms":[147],"traditional":[148],"codecs":[149],"recent":[151],"approaches,":[155],"achieving":[156],"41.67%":[158],"bitrate":[159],"reduction":[160],"compared":[161],"x265":[163],"with":[164],"medium":[165],"preset":[166],"under":[167,176],"PSNR,":[168],"obtaining":[170],"3.54%":[172],"gain":[173],"over":[174],"VVC":[175],"MS-SSIM":[178],"metric.":[179]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-06T00:00:00"}