2014 IEEE International Conference on Multimedia and Expo (ICME) (2014)
July 14, 2014 to July 18, 2014
Duan Tran , University of Illinois at Urbana Champaign
Yang Wang , University of Manitoba
David Forsyth , University of Illinois at Urbana Champaign
We address the problem of human parsing using part-based models. In particular, we consider part-based models that exploit rich pairwise relationship between parts, e.g. the color symmetry between left/right limbs. This poses a computational challenge since the state space of each part is very large, and algorithmic tricks (e.g. the distance transform) cannot be applied to handle these types of pairwise relationships. We propose to prune the state space of each part using a cascade of pruners. These pruners can filter out 99.6% of the states per part to about 500 states per part, while keeping the ground-truth states in the pruned state most of the time. In the pruned space, we can afford to apply human parsing models with more complex pairwise relationships between parts, such as the color symmetry. We demonstrate our method on a challenging human parsing dataset.
Computational modeling, Indexes, Image color analysis, Torso, Vectors, Transforms, Head
D. Tran, Y. Wang and D. Forsyth, "Human parsing with a cascade of hierarchical poselet based pruners," 2014 IEEE International Conference on Multimedia and Expo (ICME), Chengdu, China, 2014, pp. 1-6.