{"id":"https://openalex.org/W7137948097","doi":"https://doi.org/10.1609/aaai.v40i13.38038","title":"A Study of Finetuning Video Transformers for Multi-view Geometry Tasks","display_name":"A Study of Finetuning Video Transformers for Multi-view Geometry Tasks","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137948097","doi":"https://doi.org/10.1609/aaai.v40i13.38038"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i13.38038","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38038","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38038/42000","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38038/42000","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129652604","display_name":"Huimin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Huimin Wu","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661250","display_name":"Kwang-Ting Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwang-Ting Cheng","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706439","display_name":"Stephen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Stephen Lin","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121233131","display_name":"Zhirong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirong Wu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129652604"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17676408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10646","last_page":"10654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9937000274658203,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9937000274658203,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00139999995008111,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.0005000000237487257,"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/transformer","display_name":"Transformer","score":0.6617000102996826},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5436999797821045},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4361000061035156},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41190001368522644},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.36410000920295715},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.35690000653266907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869999766349792},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6617000102996826},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192999839782715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2779521785","wikidata":"https://www.wikidata.org/wiki/Q5535529","display_name":"Geometry processing","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i13.38038","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38038","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38038/42000","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38038","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38038","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38038","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38038/42000","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137948097.pdf","grobid_xml":"https://content.openalex.org/works/W7137948097.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,94],"paper":[1],"presents":[2],"an":[3],"investigation":[4],"of":[5,111,141,147,164],"vision":[6,170],"transformer":[7],"learning":[8],"for":[9,67,103],"multi-view":[10,48],"geometry":[11],"tasks,":[12],"such":[13],"as":[14],"optical":[15,104],"flow":[16,105],"estimation,":[17],"by":[18],"fine-tuning":[19],"video":[20],"foundation":[21],"models.":[22],"Unlike":[23],"previous":[24],"methods":[25],"that":[26,37,57,72],"involve":[27],"custom":[28],"architectural":[29],"designs":[30],"and":[31,64,84,114,122,144,154],"task-specific":[32],"pretraining,":[33],"our":[34],"research":[35],"finds":[36],"general-purpose":[38,58],"models":[39,166],"pretrained":[40],"on":[41,116,133],"videos":[42],"can":[43,87],"be":[44],"readily":[45],"transferred":[46],"to":[47,77,91,150],"problems":[49],"with":[50,107,138],"minimal":[51],"adaptation.":[52],"The":[53],"core":[54],"insight":[55],"is":[56],"attention":[59],"between":[60],"patches":[61],"learns":[62],"temporal":[63],"spatial":[65],"information":[66],"geometric":[68,169],"reasoning.":[69],"We":[70],"demonstrate":[71],"appending":[73],"a":[74,130],"linear":[75],"decoder":[76],"the":[78,117,134,162],"Transformer":[79],"backbone":[80],"produces":[81],"satisfactory":[82],"results,":[83],"iterative":[85],"refinement":[86],"further":[88],"elevate":[89],"performance":[90],"state-of-the-art":[92],"levels.":[93],"conceptually":[95],"simple":[96],"approach":[97],"achieves":[98],"top":[99],"cross-dataset":[100],"generalization":[101],"results":[102],"estimation":[106,153],"end-point":[108],"error":[109],"(EPE)":[110],"0.69,":[112],"1.78,":[113],"3.15":[115],"Sintel":[118,120],"clean,":[119],"final,":[121],"KITTI":[123],"datasets,":[124],"respectively.":[125],"Our":[126],"method":[127],"additionally":[128],"establishes":[129],"new":[131],"record":[132],"online":[135],"test":[136],"benchmark":[137],"EPE":[139],"values":[140],"0.79,":[142],"1.88,":[143],"F1":[145],"value":[146],"3.79.":[148],"Applications":[149],"3D":[151],"depth":[152],"stereo":[155],"matching":[156],"also":[157],"show":[158],"strong":[159],"performance,":[160],"illustrating":[161],"versatility":[163],"video-pretrained":[165],"in":[167],"addressing":[168],"tasks.":[171]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2026-03-18T00:00:00"}