Browsing Publikační činnost ČVUT by Author "Matas J."

Now showing items 1-5 of 5

    • Cumulative attribute space regression for head pose estimation and color constancy 

      Author: Chen K.; Jia K.; Huttunen H.; Matas J.; Kämäräinena J.-K.
      (Elsevier Science, 2019)
      Two-stage Cumulative Attribute (CA) regression has been found effective in regression problems of computer vision such as facial age and crowd density estimation. The first stage regression maps input features to cumulative ...

    • Discriminative Correlation Filter Tracker with Channel and Spatial Reliability 

      Author: Lukežič A.; Vojíř T.; Čehovin Zajc L.; Matas J.; Kristan M.
      (Kluwer Academic Publishers, 2018)
      Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and ...

    • Marginalizing Sample Consensus 

      Author: Baráth D.; Nosková J.; Matas J.
      (IEEE Computer Society Press, 2022)
      A new method for robust estimation, MAGSAC++, is proposed. It introduces a new model quality (scoring) function that does not make inlier-outlier decisions, and a novel marginalization procedure formulated as an M-estimation ...

    • Performance analysis of single-query 6-DoF camera pose estimation in self-driving setups 

      Author: Fu J.; Pertuz S.; Matas J.; Kamarainen J.
      (Academic Press, 2019)
      In this work, we consider the problem of single-query 6-DoF camera pose estimation, i.e. estimating the position and orientation of a camera by using reference images and a point cloud. We perform a systematic comparison ...

    • Visual Object Tracking With Discriminative Filters and Siamese Networks: A Survey and Outlook 

      Author: Javed S.; Danelljan M.; Khan F.; Khan M.; Matas J.
      (IEEE Computer Society Press, 2023)
      Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, ...