My research interests include machine learning techniques for visual tracking and probabilistic models for point cloud registration.
Paper accepted at ECCV 2016 (oral presentation)!
Two papers accepted at ICPR 2016.
In this work we develop a theoretical framework for discriminatevly learning a convolution operator in the continuous spatial domain. Our formulation enables a natural integration of multi-resolution deep feature maps. In addition, our continuous formulation is capable of accurate sub-pixel localization of the target.
In work we propose a probabilistic point set registration framework that exploits available color information associated with the points. Our method is based on a model of the joint distribution of 3D-point observations and their color information. We derive an EM algorithm for jointly estimating the model parameters and the relative transformations. The proposed model captures discriminative color information, while being computationally efficient.
In this work we propose a unified formulation for alleviating the problem of corrupted training samples in tracking-by-detection methods. This is achieved by minimizing a joint loss over both target appearance model and the training sample quality weights. Our approach is generic and can be integrated into any discriminative tracking framework.
In this work we propose Spatially Regularized Discriminative Correlation Filters (SRDCF) for tracking. This effectively mitigates the unwanted boundary effects, which limits the performance of standard correlation based trackers. The SRDCF tracker won the recent OpenCV Challenge and achieved the best result in the VOT-TIR2015 challenge.
Here we investigate the problem of accurate and fast scale estimation for visual tracking. The proposed Discriminative Scale Space Tracker (DSST) won the Visual Object Tracking (VOT) 2014 challenge.
In this work, we investigated how to incorporate color information into visual tracking.
Publications and pages