{"id":"https://openalex.org/W4298053201","doi":"https://doi.org/10.1145/3503161.3548395","title":"DeViT","display_name":"DeViT","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4298053201","doi":"https://doi.org/10.1145/3503161.3548395"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548395","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.13925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066854056","display_name":"Jiayin Cai","orcid":"https://orcid.org/0009-0007-8903-212X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayin Cai","raw_affiliation_strings":["Kuaishou Technology, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, BeiJing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700192","display_name":"Changlin Li","orcid":"https://orcid.org/0000-0002-8486-7482"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changlin Li","raw_affiliation_strings":["Kuaishou Technology, ShenZhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, ShenZhen, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037702873","display_name":"Xin Tao","orcid":"https://orcid.org/0000-0001-9126-4746"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Tao","raw_affiliation_strings":["Kuaishou Technology, ShenZhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, ShenZhen, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107916003","display_name":"Chun Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001987788","display_name":"Yu\u2010Wing Tai","orcid":"https://orcid.org/0000-0002-3148-0380"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Wing Tai","raw_affiliation_strings":["Kuaishou Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"789"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.996399998664856,"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":0.995199978351593,"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":0.7764506340026855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7244571447372437},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6348006725311279},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.565441906452179},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5583100318908691},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5490883588790894},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5012822151184082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4879545569419861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41942083835601807},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41013413667678833},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3103450536727905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14819109439849854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764506340026855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7244571447372437},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6348006725311279},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.565441906452179},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5583100318908691},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5490883588790894},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5012822151184082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4879545569419861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41942083835601807},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41013413667678833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3103450536727905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14819109439849854},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548395","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.13925","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.13925","pdf_url":"https://arxiv.org/pdf/2209.13925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.13925","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.13925","pdf_url":"https://arxiv.org/pdf/2209.13925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1487937094","https://openalex.org/W1975049209","https://openalex.org/W2069237980","https://openalex.org/W2100415658","https://openalex.org/W2115273023","https://openalex.org/W2147823818","https://openalex.org/W2331128040","https://openalex.org/W2470139095","https://openalex.org/W2475287302","https://openalex.org/W2551763541","https://openalex.org/W2601564443","https://openalex.org/W2731516742","https://openalex.org/W2785678896","https://openalex.org/W2798365772","https://openalex.org/W2886714066","https://openalex.org/W2886787375","https://openalex.org/W2907097116","https://openalex.org/W2908510526","https://openalex.org/W2947609158","https://openalex.org/W2954284167","https://openalex.org/W2963231084","https://openalex.org/W2963420272","https://openalex.org/W2969109746","https://openalex.org/W2970400386","https://openalex.org/W2982763192","https://openalex.org/W2986330308","https://openalex.org/W2986433113","https://openalex.org/W2990152177","https://openalex.org/W3035022492","https://openalex.org/W3094825490","https://openalex.org/W3095422700","https://openalex.org/W3097348442","https://openalex.org/W3144890709","https://openalex.org/W3155050726","https://openalex.org/W3171287051","https://openalex.org/W3189463461","https://openalex.org/W3201844719","https://openalex.org/W4385245566","https://openalex.org/W4394639938","https://openalex.org/W6684535058"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W3214306048","https://openalex.org/W2907830442"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,164],"novel":[4],"video":[5,168],"inpainting":[6],"architecture":[7],"named":[8],"Deformed":[9,31],"Vision":[10],"Transformers":[11,25],"(DeViT).":[12],"We":[13],"make":[14],"three":[15],"significant":[16],"contributions":[17],"to":[18,60,86,124,129],"this":[19],"task:":[20],"First,":[21],"we":[22,78,116],"extended":[23],"previous":[24,73,155],"with":[26,46,67,112,145],"patch":[27,51],"alignment":[28],"by":[29,93],"introducing":[30],"Patch-based":[32],"Homography":[33],"Estimator":[34],"(DePtH),":[35],"which":[36,72],"enriches":[37],"the":[38,80,88,101,106,118,133,136],"patch-level":[39],"feature":[40,91],"alignments":[41],"in":[42,158],"key":[43],"and":[44,99,160,162],"query":[45],"additional":[47,54],"offsets":[48],"learned":[49,139],"from":[50,140],"pairs":[52],"without":[53],"supervision.":[55],"DePtH":[56],"enables":[57],"our":[58,152],"method":[59,153],"handle":[61],"challenging":[62],"scenes":[63],"or":[64,69],"agile":[65,146],"motion":[66],"in-plane":[68],"out-of-plane":[70],"deformation,":[71],"methods":[74,157],"usually":[75],"fail.":[76],"Second,":[77],"introduce":[79,117],"Mask":[81],"Pruning-based":[82],"Patch":[83],"Attention":[84],"(MPPA)":[85],"improve":[87],"standard":[89],"patch-wised":[90],"matching":[92,107],"pruning":[94],"out":[95],"less":[96],"essential":[97],"features":[98],"considering":[100],"saliency":[102],"map.":[103],"MPPA":[104],"enhances":[105],"accuracy":[108],"between":[109],"warped":[110],"tokens":[111,131],"invalid":[113],"pixels.":[114],"Third,":[115],"Spatial-Temporal":[119],"weighting":[120],"Adaptor":[121],"(STA)":[122],"module":[123],"assign":[125],"more":[126],"accurate":[127],"attention":[128],"spatial-temporal":[130],"under":[132],"guidance":[134],"of":[135],"Deformation":[137],"Factor":[138],"DePtH,":[141],"especially":[142],"for":[143,167],"videos":[144],"motions.":[147],"Experimental":[148],"results":[149],"demonstrate":[150],"that":[151],"outperforms":[154],"state-of-the-art":[156,166],"quality":[159],"quantity":[161],"achieves":[163],"new":[165],"inpainting.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-10-01T00:00:00"}