It has always been very difficult to recognize realistic actions from unconstrained videos because there are tremendous variations from camera motion, background clutter, object a...
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
This paper presents a framework for recognising realistic human actions captured from unconstrained environments. The novelties of this work lie in three aspects. First, we propos...
Matteo Bregonzio, Jian Li, Shaogang Gong, Tao Xian...