{"id":"https://openalex.org/W7123749628","doi":"https://doi.org/10.1109/mmsp64401.2025.11324200","title":"Structure-Preserving Patch Decoding for Efficient Neural Video Representation","display_name":"Structure-Preserving Patch Decoding for Efficient Neural Video Representation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123749628","doi":"https://doi.org/10.1109/mmsp64401.2025.11324200"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5113652267","display_name":"T. Hayami","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taiga Hayami","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113807392","display_name":"K. Koizumi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kakeru Koizumi","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080047284","display_name":"H. Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Watanabe","raw_affiliation_strings":["Waseda University,Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113652267"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68850464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.31529998779296875,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.31529998779296875,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.1379999965429306,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.054499998688697815,"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/decoding-methods","display_name":"Decoding methods","score":0.6473000049591064},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.598800003528595},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5070000290870667},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4652999937534332},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4424000084400177},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4153999984264374},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.40560001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422000169754028},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6473000049591064},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092000007629395},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4424000084400177},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3758000135421753},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2563000023365021},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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":28,"referenced_works":["https://openalex.org/W2055373760","https://openalex.org/W2470139095","https://openalex.org/W2511458122","https://openalex.org/W2603777577","https://openalex.org/W3031546776","https://openalex.org/W3109585842","https://openalex.org/W3153220274","https://openalex.org/W3191617243","https://openalex.org/W3203570626","https://openalex.org/W4287756134","https://openalex.org/W4312443924","https://openalex.org/W4386065502","https://openalex.org/W4386065618","https://openalex.org/W4386075733","https://openalex.org/W4386598253","https://openalex.org/W4390871851","https://openalex.org/W4402703005","https://openalex.org/W4402703095","https://openalex.org/W4402716417","https://openalex.org/W4402727237","https://openalex.org/W4402754291","https://openalex.org/W4402816953","https://openalex.org/W4402915787","https://openalex.org/W4404719129","https://openalex.org/W4404849707","https://openalex.org/W4408862288","https://openalex.org/W4413144344","https://openalex.org/W4417281862"],"related_works":[],"abstract_inverted_index":{"Implicit":[0],"neural":[1,95],"representations":[2],"(INRs)":[3],"are":[4],"the":[5,68,132,142,156],"subject":[6],"of":[7,70,117],"extensive":[8],"research,":[9],"particularly":[10],"in":[11],"their":[12],"application":[13],"to":[14,24,33,59,84,104,127,144],"modeling":[15],"complex":[16],"signals":[17],"by":[18],"mapping":[19,30],"spatial":[20,49,81,90,134],"and":[21,54,160,169,188],"temporal":[22],"coordinates":[23],"corresponding":[25],"values.":[26],"When":[27],"handling":[28],"videos,":[29],"compact":[31],"inputs":[32],"entire":[34,64],"frames":[35,65,120],"or":[36],"spatially":[37,118],"partitioned":[38],"patch":[39,115],"images":[40,116],"is":[41],"an":[42],"effective":[43],"approach.":[44],"This":[45,129,164],"strategy":[46,153],"better":[47,189],"preserves":[48,131],"relationships,":[50],"reduces":[51,166],"computational":[52],"overhead,":[53],"improves":[55],"reconstruction":[56,69,186],"quality":[57,187],"compared":[58],"coordinate-based":[60],"mapping.":[61],"However,":[62],"predicting":[63],"often":[66],"limits":[67],"high-frequency":[71],"visual":[72],"details.":[73,163],"Additionally,":[74],"conventional":[75],"patch-based":[76],"approaches":[77],"based":[78,99],"on":[79,100,176],"uniform":[80],"partitioning":[82],"tend":[83],"introduce":[85],"boundary":[86,167],"discontinuities":[87],"that":[88,154,181],"degrade":[89],"coherence.":[91],"We":[92,140],"propose":[93],"a":[94,122,150],"video":[96,112,178],"representation":[97],"method":[98,109,183],"Structure-Preserving":[101],"Patches":[102],"(SPPs)":[103],"address":[105],"such":[106],"limitations.":[107],"Our":[108],"separates":[110],"each":[111],"frame":[113],"into":[114],"aligned":[119],"through":[121],"deterministic":[123],"pixel-based":[124],"splitting":[125],"similar":[126],"PixelUnshuffle.":[128],"operation":[130],"global":[133,157],"structure":[135],"while":[136],"allowing":[137],"patch-level":[138],"decoding.":[139],"train":[141],"decoder":[143],"reconstruct":[145],"these":[146],"structured":[147],"patches,":[148],"enabling":[149],"global-to-local":[151],"decoding":[152],"captures":[155],"layout":[158],"first":[159],"refines":[161],"local":[162],"effectively":[165],"artifacts":[168],"mitigates":[170],"distortions":[171],"from":[172],"naive":[173],"upsampling.":[174],"Experiments":[175],"standard":[177],"datasets":[179],"demonstrate":[180],"our":[182],"achieves":[184],"higher":[185],"compression":[190],"performance":[191],"than":[192],"existing":[193],"INR-based":[194],"baselines.":[195]},"counts_by_year":[],"updated_date":"2026-01-14T23:44:37.837170","created_date":"2026-01-14T00:00:00"}