R-CNNs for Pose Estimation and Action Detection

06/19/2014
by   Georgia Gkioxari, et al.
0

We present convolutional neural networks for the tasks of keypoint (pose) prediction and action classification of people in unconstrained images. Our approach involves training an R-CNN detector with loss functions depending on the task being tackled. We evaluate our method on the challenging PASCAL VOC dataset and compare it to previous leading approaches. Our method gives state-of-the-art results for keypoint and action prediction. Additionally, we introduce a new dataset for action detection, the task of simultaneously localizing people and classifying their actions, and present results using our approach.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset