We present CaPhy, a novel method for reconstructing animatable human ava...
Learning-based approaches to monocular motion capture have recently show...
For natural image matting, context information plays a crucial role in
e...
A practical long-term tracker typically contains three key properties, i...
Vision-and-Language Navigation (VLN) is unique in that it requires turni...
Scene text recognition with arbitrary shape is very challenging due to l...
Most of the existing trackers usually rely on either a multi-scale searc...
Inferring the 3D shape of an object from an RGB image has shown impressi...
Sketch recognition remains a significant challenge due to the limited
tr...
CNN-based methods have been proven to work well for saliency detection o...
Computational color constancy refers to the estimation of the scene
illu...
Recovering the 3D representation of an object from single-view or multi-...
Traditional intra prediction methods for HEVC rely on using the nearest
...
The compressed sensing (CS) has been successfully applied to image
compr...
The compressed sensing (CS) theory has been successfully applied to imag...
Recently, sparse representation based visual tracking methods have attra...