{"id":"https://openalex.org/W4387969575","doi":"https://doi.org/10.1145/3581783.3611842","title":"Diffused Fourier Network for Video Action Segmentation","display_name":"Diffused Fourier Network for Video Action Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969575","doi":"https://doi.org/10.1145/3581783.3611842"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022898952","display_name":"Borui Jiang","orcid":"https://orcid.org/0009-0008-8666-7178"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Borui Jiang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8666-7178","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong MU","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7815-3750","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5474","last_page":"5483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9980999827384949,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9961000084877014,"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":0.7656775116920471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272785663604736},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5958166122436523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4619915783405304},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.42104703187942505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.371425598859787},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3543455898761749},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.2360808253288269},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.16010832786560059},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12887808680534363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656775116920471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272785663604736},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5958166122436523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4619915783405304},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.42104703187942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.371425598859787},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3543455898761749},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.2360808253288269},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.16010832786560059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12887808680534363},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1697514459","https://openalex.org/W1901129140","https://openalex.org/W1945209586","https://openalex.org/W1953802779","https://openalex.org/W2021057537","https://openalex.org/W2098339052","https://openalex.org/W2125838338","https://openalex.org/W2127893047","https://openalex.org/W2130506643","https://openalex.org/W2151214862","https://openalex.org/W2293634267","https://openalex.org/W2412782625","https://openalex.org/W2572248355","https://openalex.org/W2594645841","https://openalex.org/W2963524571","https://openalex.org/W3034802267","https://openalex.org/W3083550439","https://openalex.org/W3119038403","https://openalex.org/W3138516171","https://openalex.org/W3155072588","https://openalex.org/W3157403981","https://openalex.org/W3166363426","https://openalex.org/W3175528029","https://openalex.org/W4206192903","https://openalex.org/W4225271941","https://openalex.org/W4249142012","https://openalex.org/W4281756776","https://openalex.org/W4312820606","https://openalex.org/W4312982010"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4395685956","https://openalex.org/W2516295475","https://openalex.org/W2766639751","https://openalex.org/W2390401148"],"abstract_inverted_index":{"Video":[0],"action":[1,16,32,50,152,164],"segmentation":[2,153],"aims":[3],"to":[4,61,155,160,200],"densely":[5],"cast":[6],"each":[7],"video":[8,31,49,57,101,213],"frame":[9],"into":[10],"a":[11,21,142,192,196],"set":[12],"of":[13,151,195],"pre-defined":[14],"human":[15],"categories.":[17],"This":[18],"work":[19],"proposes":[20],"novel":[22],"model,":[23],"dubbed":[24],"as":[25,84,167,181],"diffused":[26],"Fourier":[27,92,110,137],"network":[28],"(DFN)":[29],"for":[30,48,64,70,113,145],"segmentation.":[33,51],"It":[34],"advances":[35],"the":[36,45,67,100,105,131,149,161,170,174,184,201,206,223],"research":[37],"frontier":[38],"by":[39,173],"addressing":[40],"several":[41],"central":[42],"bottlenecks":[43],"in":[44,85,99,169,205],"existing":[46,146],"methods":[47],"First,":[52],"capturing":[53],"long-range":[54],"dependence":[55],"among":[56],"frames":[58],"is":[59],"known":[60,166],"be":[62,156],"crucial":[63],"precisely":[65],"estimating":[66],"temporal":[68,97,133,186],"boundaries":[69],"actions.":[71],"Rather":[72],"than":[73],"relying":[74],"on":[75,211],"compute-intensive":[76],"self-attention":[77],"modules":[78],"or":[79],"stacking":[80],"multi-rate":[81],"dilated":[82],"convolutions":[83],"previous":[86],"models":[87],"(e.g.,":[88,123],"ASFormer),":[89],"we":[90,178],"devise":[91],"token":[93,138],"mixer":[94,139],"over":[95],"shiftable":[96],"windows":[98],"sequence,":[102],"which":[103],"harnesses":[104],"parameter-free":[106],"and":[107,188,217,236],"light-weighted":[108],"Fast":[109],"Transform":[111],"(FFT)":[112],"efficient":[114],"spectral-temporal":[115],"feature":[116],"learning.":[117],"Essentially,":[118],"even":[119],"simple":[120],"spectral":[121],"operations":[122],"pointwise":[124],"product)":[125],"bring":[126],"global":[127],"receptive":[128],"field":[129],"across":[130],"entire":[132],"window.":[134],"The":[135],"proposed":[136,224],"thus":[140],"provides":[141],"low-cost":[143],"alternative":[144],"practice.":[147],"Secondly,":[148],"results":[150],"tend":[154],"fragmented,":[157],"primarily":[158],"due":[159],"noisy":[162],"per-frame":[163],"likelihood,":[165],"over-segmentation":[168],"literature.":[171],"Inspired":[172],"recently-proposed":[175],"diffusion":[176,207],"models,":[177],"treat":[179],"over-segments":[180],"noises":[182],"corrupting":[183],"true":[185],"boundaries,":[187],"conduct":[189],"denoising":[190,203],"via":[191],"recurrent":[193],"execution":[194],"parameter-sharing":[197],"module,":[198],"akin":[199],"backward":[202],"process":[204],"models.":[208],"Comprehensive":[209],"experiments":[210],"three":[212],"benchmarks":[214],"(GTEA,":[215],"50salads":[216],"Breakfast)":[218],"have":[219],"clearly":[220],"validated":[221],"that":[222],"method":[225],"can":[226],"strike":[227],"an":[228],"excellent":[229],"balance":[230],"between":[231],"computations":[232],"/":[233],"parameter":[234],"count":[235],"accuracy.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}