{"id":"https://openalex.org/W4403094596","doi":"https://doi.org/10.1109/tpami.2024.3463648","title":"Optical Flow as Spatial-Temporal Attention Learners","display_name":"Optical Flow as Spatial-Temporal Attention Learners","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4403094596","doi":"https://doi.org/10.1109/tpami.2024.3463648","pmid":"https://pubmed.ncbi.nlm.nih.gov/39361459"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3463648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3463648","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103247375","display_name":"Yawen Lu","orcid":"https://orcid.org/0000-0001-8046-3045"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yawen Lu","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-8046-3045","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325126","display_name":"Cheng Han","orcid":"https://orcid.org/0000-0002-8145-3436"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Han","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-8145-3436","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, New York City, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-7570-5756","affiliations":[{"raw_affiliation_string":"Meta AI, New York City, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047220188","display_name":"Heng Fan","orcid":"https://orcid.org/0000-0002-7033-3690"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Fan","raw_affiliation_strings":["University of North Texas, Denton, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-7033-3690","affiliations":[{"raw_affiliation_string":"University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017663923","display_name":"Zhaodan Kong","orcid":"https://orcid.org/0000-0002-2493-1366"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodan Kong","raw_affiliation_strings":["University of California, Davis, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2493-1366","affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979289","display_name":"Dongfang Liu","orcid":"https://orcid.org/0000-0001-6995-4775"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-6995-4775","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409186","display_name":"Yingjie Chen","orcid":"https://orcid.org/0000-0001-6705-3535"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingjie Chen","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6705-3535","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7895,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90986222,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"11491","last_page":"11506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.810699999332428,"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/T10320","display_name":"Neural Networks and Applications","score":0.7641000151634216,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/optical-flow","display_name":"Optical flow","score":0.6852530241012573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614773273468018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5207490921020508},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4566762149333954},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4281575083732605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1679365336894989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11111190915107727}],"concepts":[{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6852530241012573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614773273468018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5207490921020508},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4566762149333954},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4281575083732605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1679365336894989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11111190915107727},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3463648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3463648","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39361459","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39361459","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G377155036","display_name":"CRII: RI: Vision-Anchored Automation of Bird-Sized UAVs in Unknown Cluttered Indoor Environments","funder_award_id":"2242243","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4787178636","display_name":null,"funder_award_id":"NR233A750004G044","funder_id":"https://openalex.org/F4320332782","funder_display_name":"Natural Resources Conservation Service"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332782","display_name":"Natural Resources Conservation Service","ror":"https://ror.org/03j7rgg33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W181676623","https://openalex.org/W764651262","https://openalex.org/W1508115313","https://openalex.org/W1513100184","https://openalex.org/W1993850091","https://openalex.org/W2017849585","https://openalex.org/W2024336175","https://openalex.org/W2098500213","https://openalex.org/W2117539524","https://openalex.org/W2129671742","https://openalex.org/W2153101587","https://openalex.org/W2155302366","https://openalex.org/W2259424905","https://openalex.org/W2286655030","https://openalex.org/W2492517581","https://openalex.org/W2560474170","https://openalex.org/W2560533888","https://openalex.org/W2810554001","https://openalex.org/W2890949887","https://openalex.org/W2896457183","https://openalex.org/W2902346020","https://openalex.org/W2949023359","https://openalex.org/W2952825894","https://openalex.org/W2962771259","https://openalex.org/W2963093735","https://openalex.org/W2963265330","https://openalex.org/W2963583471","https://openalex.org/W2963652593","https://openalex.org/W2963782415","https://openalex.org/W2964110616","https://openalex.org/W2964156315","https://openalex.org/W2964677288","https://openalex.org/W2970881233","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W3000161127","https://openalex.org/W3013402579","https://openalex.org/W3034514115","https://openalex.org/W3034642839","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3106619925","https://openalex.org/W3106932526","https://openalex.org/W3107540572","https://openalex.org/W3109908659","https://openalex.org/W3121523901","https://openalex.org/W3147597595","https://openalex.org/W3173561529","https://openalex.org/W3174911623","https://openalex.org/W3175682855","https://openalex.org/W3176336346","https://openalex.org/W3186096360","https://openalex.org/W3188394685","https://openalex.org/W3196288474","https://openalex.org/W3201844719","https://openalex.org/W3201987110","https://openalex.org/W3202487934","https://openalex.org/W4205982568","https://openalex.org/W4214493665","https://openalex.org/W4226151448","https://openalex.org/W4249022109","https://openalex.org/W4312253171","https://openalex.org/W4312275038","https://openalex.org/W4312636847","https://openalex.org/W4312713936","https://openalex.org/W4312770027","https://openalex.org/W4312790276","https://openalex.org/W4312812783","https://openalex.org/W4312841802","https://openalex.org/W4312986923","https://openalex.org/W4313156423","https://openalex.org/W4313177625","https://openalex.org/W4385245566","https://openalex.org/W4386076238","https://openalex.org/W6687484953","https://openalex.org/W6723083950","https://openalex.org/W6754801538","https://openalex.org/W6757585730","https://openalex.org/W6759534164","https://openalex.org/W6773019456","https://openalex.org/W6780100354","https://openalex.org/W6784333009","https://openalex.org/W6785287398","https://openalex.org/W6792695861","https://openalex.org/W6796761347","https://openalex.org/W6838332116","https://openalex.org/W6843355076","https://openalex.org/W6845518869"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Optical":[0],"flow":[1,45,66,95,139,201,204],"is":[2],"an":[3],"indispensable":[4],"building":[5],"block":[6],"for":[7,32,43,114,198,209],"various":[8],"important":[9],"computer":[10],"vision":[11],"tasks,":[12,161],"including":[13,162],"motion":[14,92],"estimation,":[15,205],"object":[16,164],"tracking,":[17],"and":[18,62,72,91,116,123,152,178,202,212],"disparity":[19],"measurement.":[20],"To":[21],"date,":[22],"the":[23,112,167,175,182,188],"dominant":[24,49],"methods":[25],"are":[26],"CNN-based,":[27],"leaving":[28],"plenty":[29],"of":[30,125,190],"room":[31],"improvement.":[33],"In":[34],"this":[35],"work,":[36],"we":[37],"propose":[38],"TransFlow,":[39],"a":[40,107,195],"transformer":[41],"architecture":[42],"optical":[44,200],"estimation.":[46,140],"Compared":[47],"to":[48,78,129],"CNN-based":[50],"methods,":[51],"TransFlow":[52,126,191],"demonstrates":[53],"three":[54],"advantages.":[55],"First,":[56],"it":[57,84,105,193],"provides":[58],"more":[59,86],"accurate":[60],"correlation":[61],"trustworthy":[63],"matching":[64],"in":[65,94,101,136],"estimation":[67,96],"by":[68],"utilizing":[69],"spatial":[70],"self-attention":[71],"cross-attention":[73],"mechanisms":[74],"between":[75],"adjacent":[76],"frames":[77],"effectively":[79],"capture":[80],"global":[81],"dependencies;":[82],"Second,":[83],"recovers":[85],"compromised":[87],"information":[88],"(e.g.,":[89],"occlusion":[90],"blur)":[93],"through":[97],"long-range":[98],"temporal":[99],"association":[100],"dynamic":[102],"scenes;":[103],"Third,":[104],"introduces":[106],"concise":[108],"self-learning":[109],"paradigm,":[110],"eliminating":[111],"need":[113],"complex":[115],"laborious":[117],"multi-stage":[118],"pre-training":[119],"procedures.":[120],"The":[121],"versatility":[122],"superiority":[124],"extend":[127],"seamlessly":[128],"3D":[130,137],"scene":[131,138,203],"motion,":[132],"yielding":[133],"competitive":[134],"outcomes":[135],"Our":[141],"approach":[142],"attains":[143],"state-of-the-art":[144],"results":[145],"on":[146,159],"benchmark":[147],"datasets":[148],"such":[149],"as":[150,194],"Sintel":[151],"KITTI-15,":[153],"while":[154],"also":[155],"exhibiting":[156],"exceptional":[157],"performance":[158],"downstream":[160],"video":[163,171,179],"detection":[165],"using":[166,174,181],"ImageNet":[168],"VID":[169],"dataset,":[170,177],"frame":[172],"interpolation":[173],"GoPro":[176],"stabilization":[180],"DeepStab":[183],"dataset.":[184],"We":[185],"believe":[186],"that":[187],"effectiveness":[189],"positions":[192],"flexible":[196],"baseline":[197],"both":[199],"offering":[206],"promising":[207],"avenues":[208],"future":[210],"research":[211],"development.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}