{"id":"https://openalex.org/W4221145487","doi":"https://doi.org/10.1109/icassp43922.2022.9746665","title":"Deformable VisTR: Spatio Temporal Deformable Attention for Video Instance Segmentation","display_name":"Deformable VisTR: Spatio Temporal Deformable Attention for Video Instance Segmentation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221145487","doi":"https://doi.org/10.1109/icassp43922.2022.9746665"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746665","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.06318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018925851","display_name":"Sudhir Yarram","orcid":"https://orcid.org/0000-0002-7986-3778"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudhir Yarram","raw_affiliation_strings":["University at Buffalo"],"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018838133","display_name":"Jiong Wu","orcid":"https://orcid.org/0000-0001-8045-9417"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialian Wu","raw_affiliation_strings":["University at Buffalo"],"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pan Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Ji","raw_affiliation_strings":["InnoPeak Technology Inc.,OPPO US Research Center"],"affiliations":[{"raw_affiliation_string":"InnoPeak Technology Inc.,OPPO US Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["InnoPeak Technology Inc.,OPPO US Research Center"],"affiliations":[{"raw_affiliation_string":"InnoPeak Technology Inc.,OPPO US Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7901-8793"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["University at Buffalo"],"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018925851"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.0597,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22323139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3303","last_page":"3307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.15929999947547913,"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/T11439","display_name":"Video Analysis and Summarization","score":0.15929999947547913,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14650000631809235,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.1446000039577484,"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":0.8434751033782959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7075372934341431},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6793351173400879},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5832631587982178},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5772507786750793},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5655588507652283},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4998908042907715},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4453333020210266},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4371013641357422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35298943519592285},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3156587481498718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08869671821594238},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07947787642478943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434751033782959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7075372934341431},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6793351173400879},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5832631587982178},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5772507786750793},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5655588507652283},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4998908042907715},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4453333020210266},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4371013641357422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35298943519592285},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3156587481498718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08869671821594238},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07947787642478943},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746665","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.06318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06318","pdf_url":"https://arxiv.org/pdf/2203.06318","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.06318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.06318","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/7qwd-7303","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7qwd-7303","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.06318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06318","pdf_url":"https://arxiv.org/pdf/2203.06318","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6776148482","display_name":null,"funder_award_id":"CNS1951952","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7203018584","display_name":"SCC-PG: Towards cybernetic buildings: integrated intelligent sensing to create responsive environments","funder_award_id":"1951952","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221145487.pdf","grobid_xml":"https://content.openalex.org/works/W4221145487.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2963150697","https://openalex.org/W2963849369","https://openalex.org/W2982723417","https://openalex.org/W2987761193","https://openalex.org/W3034499084","https://openalex.org/W3109372619","https://openalex.org/W3139267983","https://openalex.org/W3169933013","https://openalex.org/W3171516518","https://openalex.org/W3181286780","https://openalex.org/W3202509201","https://openalex.org/W6739901393","https://openalex.org/W6778485988","https://openalex.org/W6784094891","https://openalex.org/W6787212282"],"related_works":["https://openalex.org/W1469282","https://openalex.org/W5999557","https://openalex.org/W16764832","https://openalex.org/W10029978","https://openalex.org/W1366435","https://openalex.org/W8031603","https://openalex.org/W2893967","https://openalex.org/W11321453","https://openalex.org/W6473745","https://openalex.org/W11555516"],"abstract_inverted_index":{"Video":[0],"instance":[1],"segmentation":[2],"(VIS)":[3],"task":[4],"requires":[5],"classifying,":[6],"segmenting,":[7],"and":[8],"tracking":[9],"object":[10],"instances":[11],"over":[12],"all":[13],"frames":[14],"in":[15,97],"a":[16,76,86],"video":[17],"clip.":[18],"Recently,":[19],"VisTR":[20,35,92,114],"[1]":[21],"has":[22],"been":[23],"proposed":[24],"as":[25,111],"end-to-end":[26],"transformer-based":[27],"VIS":[28],"framework,":[29],"while":[30],"demonstrating":[31],"state-of-the-art":[32],"performance.":[33],"However,":[34],"is":[36,133],"slow":[37],"to":[38,48,75,93],"converge":[39],"during":[40],"training,":[41],"requiring":[42],"around":[43,85],"1000":[44],"GPU":[45,118],"hours":[46],"due":[47],"the":[49,60,98,112,123,129],"high":[50],"computational":[51],"cost":[52],"of":[53,80,100,125],"its":[54],"transformer":[55],"attention":[56,70],"module.":[57],"To":[58],"improve":[59],"training":[61,119],"efficiency,":[62],"we":[63],"propose":[64],"Deformable":[65,91],"VisTR,":[66],"leveraging":[67],"spatio-temporal":[68,82,101],"deformable":[69],"module":[71],"that":[72],"only":[73],"attends":[74],"small":[77],"fixed":[78],"set":[79],"key":[81],"sampling":[83],"points":[84],"reference":[87],"point.":[88],"This":[89],"enables":[90],"achieve":[94,107],"linear":[95],"computation":[96],"size":[99],"feature":[102],"maps.":[103],"Moreover,":[104],"it":[105],"can":[106],"on":[108,128],"par":[109],"performance":[110],"original":[113],"with":[115],"10\u00d7":[116],"less":[117],"hours.":[120],"We":[121],"validate":[122],"effectiveness":[124],"our":[126],"method":[127],"Youtube-VIS":[130],"benchmark.":[131],"Code":[132],"available":[134],"at":[135],"https://github.com/skrya/DefVIS.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2022-04-03T00:00:00"}