Linear subspace learning (LSL) is a popular approach to image recognition and it aims to reveal the essential features of high dimensional data, e.g., facial images, in a lower di...
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Background modelling on tensor field has recently been proposed for foreground detection tasks. Taking into account the Riemannian structure of the tensor manifold, recent resear...
Rui Caseiro, João F. Henriques, Pedro Martins, Jo...