Sökning: "Martin Danelljan"

Hittade 3 avhandlingar innehållade orden Martin Danelljan.

  1. 1. Learning Convolution Operators for Visual Tracking

    Författare :Martin Danelljan; Michael Felsberg; Fahad Shahbaz Khan; Jiri Matas; Linköpings universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Visual tracking is one of the fundamental problems in computer vision. Its numerous applications include robotics, autonomous driving, augmented reality and 3D reconstruction. In essence, visual tracking can be described as the problem of estimating the trajectory of a target in a sequence of images. LÄS MER

  3. 2. Towards Accurate and Reliable Deep Regression Models

    Författare :Fredrik K. Gustafsson; Thomas B. Schön; Martin Danelljan; Søren Hauberg; Uppsala universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Machine Learning; Deep Learning; Regression; Probabilistic Models; Energy-Based Models; Uncertainty Estimation; Machine learning; Maskininlärning;

    Sammanfattning : Regression is a fundamental machine learning task with many important applications within computer vision and other domains. In general, it entails predicting continuous targets from given inputs. LÄS MER

  4. 3. Dynamic Visual Learning

    Författare :Joakim Johnander; Michael Felsberg; Martin Danelljan; Nicholas Wickström; Bernt Schiele; Linköpings universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Autonomous robots act in a \emph{dynamic} world where both the robots and other objects may move. The surround sensing systems of said robots therefore work with dynamic input data and need to estimate both the current state of the environment as well as its dynamics. LÄS MER