. . "P(GAP103/10/1585)" . . "VISIGRAPP 2010: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications" . . "Set\u00FAbal" . . . . "2010-05-17+02:00"^^ . . "[CE58D337A798]" . "Angers" . "RIV/68407700:21230/10:00175502" . "RIV/68407700:21230/10:00175502!RIV11-GA0-21230___" . . . . "Incremental learning and validation of sequential predictors in video browsing application"@en . "2"^^ . "263389" . . "Svoboda, Tom\u00E1\u0161" . "8"^^ . "Institute for Systems and Technologies of Information, Control and Communication" . . "978-989-674-028-3" . . "2"^^ . "Incremental learning and validation of sequential predictors in video browsing application"@en . "Hurych, David" . . "21230" . "Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is done by clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-lengt"@en . "Incremental learning and validation of sequential predictors in video browsing application" . . "Incremental learning and validation of sequential predictors in video browsing application" . . "Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is done by clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-lengt" . . . . "predictors; incremental; learning; validation; video; browsing"@en .