Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/
For object recognition, the current state-of-the-art is based on exhaustive search. However, to ...
While supervised learning approaches for 3D shape retrieval have been successfully used to incorporate human knowledge about object classes based on global shape features, the inc...
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase feature [3]) in terms of their distinctiveness, detectability, and robustness to i...
Actions are spatio-temporal patterns which can be characterized
by collections of spatio-temporal invariant features.
Detection of actions is to find the re-occurrences
(e.g. th...