Learn More
Discovering visual dynamics during human actions is a challenging task for human action recognition. To deal with this problem, we theoretically propose the multi-task conditional random fields model and explore its application on human action recognition. For visual representation, we propose the part-induced spatiotemporal action unit sequence to(More)
This paper originally proposes the clique-graph and further presents a clique-graph matching method by preserving global and local structures. Especially, we formulate the objective function of clique-graph matching with respective to two latent variables, the clique information in the original graph and the pairwise clique correspondence constrained by the(More)
View-based 3-D model retrieval is one of the most important techniques in numerous applications of computer vision. While many methods have been proposed in recent years, to the best of our knowledge, there is no benchmark to evaluate the state-of-the-art methods. To tackle this problem, we systematically investigate and evaluate the related methods by: 1)(More)
Attributes are expected to narrow down the semantic gap between low-level visual features and high-level semantic meanings. Such superiority motivates us to explore pedestrian attributes which has became a critical problem to boost image understanding and improve the performance of pedestrian detection, retrieval, re-identification, etc. Based on the PETA(More)
  • 1