{"id":"https://openalex.org/W2136912046","doi":"https://doi.org/10.1109/icip.2004.1421626","title":"Audio-visual flow - a variational approach to multi-modal flow estimation","display_name":"Audio-visual flow - a variational approach to multi-modal flow estimation","publication_year":2005,"publication_date":"2005-04-19","ids":{"openalex":"https://openalex.org/W2136912046","doi":"https://doi.org/10.1109/icip.2004.1421626","mag":"2136912046"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2004.1421626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2004.1421626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Image Processing, 2004. ICIP '04.","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/A5012139103","display_name":"Roszilah Hamid","orcid":"https://orcid.org/0000-0002-4617-970X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Hamid","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014205993","display_name":"Aaron Bobick","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Bobick","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014124403","display_name":"Anthony Yezzi","orcid":"https://orcid.org/0000-0002-3771-4889"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Yezzi","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"2563","last_page":"2566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9983000159263611,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.9865000247955322,"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":0.7075560688972473},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5668097138404846},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5578626990318298},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.546351969242096},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.541724443435669},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5297861099243164},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4932233691215515},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48204073309898376},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4808131456375122},{"id":"https://openalex.org/keywords/information-flow","display_name":"Information flow","score":0.47388190031051636},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46127745509147644},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.45652714371681213},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4387095868587494},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4373904764652252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4356027841567993},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38265836238861084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36572057008743286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19912999868392944},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1357349455356598},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09532493352890015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075560688972473},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5668097138404846},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5578626990318298},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.546351969242096},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.541724443435669},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5297861099243164},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4932233691215515},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48204073309898376},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4808131456375122},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.47388190031051636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46127745509147644},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.45652714371681213},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4387095868587494},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4373904764652252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4356027841567993},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38265836238861084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36572057008743286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19912999868392944},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1357349455356598},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09532493352890015},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icip.2004.1421626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2004.1421626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Image Processing, 2004. ICIP '04.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.9186","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.9186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~raffay/ICIP_2004_Camera_Ready.pdf","raw_type":"text"},{"id":"pmh:oai:smartech.gatech.edu:1853/48953","is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/48953","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W76866493","https://openalex.org/W1578285471","https://openalex.org/W1970763416","https://openalex.org/W2100315781","https://openalex.org/W2118877769","https://openalex.org/W2157622201","https://openalex.org/W4285719527","https://openalex.org/W6677548441"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Just":[0],"as":[1,23],"a":[2,8,24,32,61,132],"motion":[3],"field":[4,13,29],"is":[5,91],"associated":[6,16],"to":[7,17,105,120,135],"moving":[9],"object,":[10],"an":[11,18,43,48,86],"audio":[12,49,87],"can":[14,21,130],"be":[15],"object":[19],"that":[20],"behave":[22],"sound":[25,33],"source.":[26],"The":[27,73,100],"flow":[28],"of":[30,79],"such":[31],"source":[34],"which":[35,90],"moves":[36],"over":[37],"time":[38],"would":[39],"not":[40],"only":[41],"have":[42],"optical":[44],"component,":[45],"but":[46],"also":[47],"component;":[50],"something":[51],"we":[52,59],"call":[53],"audio-visual":[54],"flow.":[55],"In":[56],"this":[57],"paper":[58],"present":[60],"common":[62],"structure":[63,82],"tensor":[64,83],"based":[65,109],"variational":[66],"framework":[67,129],"for":[68],"dense":[69],"audiovisual":[70],"flow-field":[71],"estimation.":[72],"proposed":[74,128],"scheme":[75,101],"improves":[76],"the":[77,80,95,111],"rank":[78],"local":[81],"by":[84],"incorporating":[85],"information":[88,98],"channel":[89],"substantially":[92],"uncorrelated":[93],"from":[94],"complementing":[96],"visual":[97,138],"channel.":[99],"allows":[102],"ascribing":[103],"weights":[104],"individual":[106],"sensor":[107],"modalities":[108,125],"on":[110],"confidence":[112],"in":[113,126],"their":[114],"corresponding":[115],"measurements.":[116],"Results":[117],"are":[118],"presented":[119],"demonstrate":[121],"how":[122],"combining":[123],"multiple":[124],"our":[127],"provide":[131],"possible":[133],"solution":[134],"temporary":[136],"full":[137],"occlusions.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}