Sparse dictionary-based representation and recognition of action attributes

TitleSparse dictionary-based representation and recognition of action attributes
Publication TypeConference Papers
Year of Publication2011
AuthorsQiu Q, Zhuolin Jiang, Chellappa R
Conference Name2011 IEEE International Conference on Computer Vision (ICCV)
Date Published2011/11/06/13
ISBN Number978-1-4577-1101-5
Keywordsaction attributes, appearance information, class distribution, Dictionaries, dictionary learning process, Encoding, Entropy, Gaussian process model, Gaussian processes, Histograms, HUMANS, Image coding, image representation, information maximization, learning (artificial intelligence), modeled action categories, Mutual information, Object recognition, probabilistic logic, sparse coding property, sparse dictionary-based recognition, sparse dictionary-based representation, sparse feature space, unmodeled action categories

We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary item. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with a compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition applications.