{"id":"https://openalex.org/W4401878721","doi":"https://doi.org/10.1109/tip.2024.3446228","title":"Spatio-Temporal Convolutional Neural Network for Enhanced Inter Prediction in Video Coding","display_name":"Spatio-Temporal Convolutional Neural Network for Enhanced Inter Prediction in Video Coding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401878721","doi":"https://doi.org/10.1109/tip.2024.3446228","pmid":"https://pubmed.ncbi.nlm.nih.gov/39186411"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3446228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2024.3446228","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tip.2024.3446228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097530896","display_name":"Philipp Merkle","orcid":"https://orcid.org/0009-0004-6646-3208"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Merkle","raw_affiliation_strings":["Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0004-6646-3208","affiliations":[{"raw_affiliation_string":"Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059582611","display_name":"Martin Winken","orcid":"https://orcid.org/0000-0003-2597-8470"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Winken","raw_affiliation_strings":["Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2597-8470","affiliations":[{"raw_affiliation_string":"Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048686054","display_name":"Jonathan Pfaff","orcid":"https://orcid.org/0000-0002-3550-0596"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Pfaff","raw_affiliation_strings":["Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3550-0596","affiliations":[{"raw_affiliation_string":"Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056193742","display_name":"Heiko Schwarz","orcid":"https://orcid.org/0000-0002-7136-0041"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heiko Schwarz","raw_affiliation_strings":["Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7136-0041","affiliations":[{"raw_affiliation_string":"Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083836367","display_name":"Detlev Marpe","orcid":"https://orcid.org/0000-0002-5391-3247"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Detlev Marpe","raw_affiliation_strings":["Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5391-3247","affiliations":[{"raw_affiliation_string":"Video Communication and Applications Department, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034084717","display_name":"Thomas Wiegand","orcid":"https://orcid.org/0000-0002-1121-2581"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Wiegand","raw_affiliation_strings":["Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1121-2581","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany","institution_ids":["https://openalex.org/I2800274787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800274787"],"apc_list":null,"apc_paid":null,"fwci":2.2481,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89253061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"4738","last_page":"4752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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":0.8042843341827393},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7686029672622681},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6103829145431519},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6030352115631104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47619569301605225},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.47248831391334534},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4643210768699646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45316919684410095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4161544442176819},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11649763584136963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042843341827393},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7686029672622681},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6103829145431519},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6030352115631104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47619569301605225},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.47248831391334534},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4643210768699646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45316919684410095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4161544442176819},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11649763584136963},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2024.3446228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2024.3446228","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:39186411","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39186411","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:publica.fraunhofer.de:publica/499192","is_oa":true,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/499192","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/tip.2024.3446228","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2024.3446228","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2042023007","https://openalex.org/W2101700394","https://openalex.org/W2110440242","https://openalex.org/W2126897420","https://openalex.org/W2137983211","https://openalex.org/W2147800946","https://openalex.org/W2153721920","https://openalex.org/W2171080137","https://openalex.org/W2195682172","https://openalex.org/W2476548250","https://openalex.org/W2612846844","https://openalex.org/W2791933231","https://openalex.org/W2793408333","https://openalex.org/W2802934755","https://openalex.org/W2891736150","https://openalex.org/W2896406755","https://openalex.org/W2896754546","https://openalex.org/W2913664580","https://openalex.org/W2935381027","https://openalex.org/W2942820541","https://openalex.org/W2963626582","https://openalex.org/W2969260367","https://openalex.org/W2991484220","https://openalex.org/W2992051623","https://openalex.org/W2999940418","https://openalex.org/W3035195755","https://openalex.org/W3035379862","https://openalex.org/W3133940464","https://openalex.org/W3134670382","https://openalex.org/W3166014221","https://openalex.org/W3169596802","https://openalex.org/W3172995745","https://openalex.org/W3186764622","https://openalex.org/W3188610266","https://openalex.org/W3194454673","https://openalex.org/W3196358730","https://openalex.org/W3202918664","https://openalex.org/W4308233960","https://openalex.org/W6631190155","https://openalex.org/W6631943919"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W4293226380","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W3203142394","https://openalex.org/W4242191701"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,29,51,91,100,151,166],"convolutional":[4],"neural":[5,47],"network":[6],"(CNN)-based":[7],"enhancement":[8],"to":[9,71,79,95],"inter":[10,26,116],"prediction":[11,23,74,117],"in":[12,83,99,114],"Versatile":[13],"Video":[14],"Coding":[15],"(VVC).":[16],"Our":[17],"approach":[18],"aims":[19],"at":[20],"improving":[21],"the":[22,43,69,73,80,96,115,124,127,135,138,183,193],"signal":[24,55,59,75,82,153],"of":[25,54,126,137,178,192],"blocks":[27,142],"with":[28],"residual":[30],"CNN":[31,97,128,139],"that":[32,46,63,89,123,155],"incorporates":[33],"spatial":[34,111],"and":[35,62,107,180,187],"temporal":[36],"reference":[37,66,112,159],"samples.":[38],"It":[39],"is":[40,119],"motivated":[41],"by":[42,76,149],"theoretical":[44],"consideration":[45],"network-based":[48],"methods":[49,61],"have":[50,68],"higher":[52],"degree":[53],"adaptivity":[56],"than":[57],"conventional":[58],"processing":[60],"spatially":[64],"neighboring":[65],"samples":[67,113],"potential":[70],"improve":[72],"adapting":[77],"it":[78],"reconstructed":[81],"its":[84],"immediate":[85],"vicinity.":[86],"We":[87,146],"show":[88,173],"adding":[90],"polyphase":[92],"decomposition":[93],"stage":[94],"results":[98,172],"significantly":[101],"better":[102],"trade-off":[103],"between":[104],"computational":[105],"complexity":[106],"coding":[108],"performance.":[109],"Incorporating":[110],"process":[118],"challenging:":[120],"The":[121],"fact":[122],"input":[125],"for":[129,140,182],"one":[130],"block":[131],"may":[132],"depend":[133],"on":[134],"output":[136],"preceding":[141],"prohibits":[143],"parallel":[144,162],"processing.":[145],"solve":[147],"this":[148],"introducing":[150],"novel":[152],"plane":[154],"contains":[156],"specifically":[157],"constrained":[158],"samples,":[160],"enabling":[161],"decoding":[163],"while":[164],"maintaining":[165],"high":[167],"compression":[168],"efficiency.":[169],"Overall,":[170],"experimental":[171],"average":[174],"bit":[175],"rate":[176],"savings":[177],"4.07%":[179],"3.47%":[181],"random":[184],"access":[185],"(RA)":[186],"low-delay":[188],"B":[189],"(LB)":[190],"configurations":[191],"JVET":[194],"common":[195],"test":[196],"conditions,":[197],"respectively.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}