Our paper on convolutional random projection forests is accepted to PAMI

[2017.11.25]

The following paper is accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI):

  • Head and Body Orientation Estimation Using Convolutional Random Projection Forests by Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh
    • Abstract: In this paper, we consider the problem of estimating the head pose and body orientation of a person from a low-resolution image. Under this setting, it is difficult to reliably extract facial features or detect body parts. We propose a convolutional random projection forest (CRPforest) algorithm for these tasks. A convolutional random projection network (CRPnet) is used at each node of the forest. It maps an input image to a high-dimensional feature space using a rich filter bank. The filter bank is designed to generate sparse responses so that they can be efficiently computed by compressive sensing. A sparse random projection matrix can capture most essential information contained in the filter bank without using all the filters in it. Therefore, the CRPnet is fast, e.g., it requires 0.04ms to process an image of 50x50 pixels, due to the small number of convolutions (e.g., 0.01% of a layer of a neural network) at the expense of less than 2% accuracy. The overall forest estimates head and body pose well on benchmark datasets, e.g., over 98% on the HIIT dataset, while requiring at 3.8ms without using a GPU. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in low-resolution images with noise, occlusion, and motion blur.