Search Results for author: Guang Shu

Found 5 papers, 2 papers with code

DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network

2 code implementations14 Feb 2017 Afshin Dehghan, Enrique. G. Ortiz, Guang Shu, Syed Zain Masood

This paper describes the details of Sighthound's fully automated age, gender and emotion recognition system.

Emotion Recognition

View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network

1 code implementation6 Feb 2017 Afshin Dehghan, Syed Zain Masood, Guang Shu, Enrique. G. Ortiz

The backbone of our system is a deep convolutional neural network that is not only computationally inexpensive, but also provides state-of-the-art results on several competitive benchmarks.

Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video

no code implementations CVPR 2013 Yang Yang, Guang Shu, Mubarak Shah

In order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders.

object-detection Object Detection

Improving an Object Detector and Extracting Regions Using Superpixels

no code implementations CVPR 2013 Guang Shu, Afshin Dehghan, Mubarak Shah

In general, our method takes detection bounding boxes of a generic detector as input and generates the detection output with higher average precision and precise object regions.

Object Superpixels

Cannot find the paper you are looking for? You can Submit a new open access paper.