This paper presents a framework for image parsing with multiple label sets. For example, we may want to simultaneously label every image region according to its basiclevel object ...
This paper presents a novel schema to address the polysemy of visual words in the widely used bag-of-words model. As a visual word may have multiple meanings, we show it is possib...
Recently, hashing based Approximate Nearest Neighbor (ANN) techniques have been attracting lots of attention in computer vision. The data-dependent hashing methods, e.g., Spectral...
Hao Xu, Jingdong Wang, Zhu Li, Gang Zeng, Shipeng ...
In the security domain a key problem is identifying rare behaviours of interest. Training examples for these behaviours may or may not exist, and if they do exist there will be fe...
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dense flow field, appropriate spatial constraints have to be enforced. Recent ad...
In recent years, depth cameras have become a widely available sensor type that captures depth images at realtime frame rates. Even though recent approaches have shown that 3D pose...
Andreas Baak, Meinard Muller, Gaurav Bharaj, Hans-...
In this paper, we propose a physically-based dynamical model for tracking. Our model relies on Newton’s second law of motion, which governs any real-world dynamical system. As a...
In this paper we propose a new method for the simultaneous segmentation and 3D reconstruction of interest point based articulated motion. We decompose a set of point tracks into r...
We introduce a spatially dense variational approach to estimate the calibration of multiple cameras in the context of 3D reconstruction. We propose a relaxation scheme which allow...