Workshop Program

Prof. Rama Chellappa is a Minta Martin Professor of Engineering and Chair of the ECE department at the University of Maryland. Prof. Chellappa received the K.S. Fu Prize from the International Association of Pattern Recognition (IAPR). He is a recipient of the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society. He also received the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society. At UMD, he received college and university level recognitions for research, teaching innovation and mentoring of undergraduate students. In 2010, he was recognized as an Outstanding ECE by Prude university. Prof. Chellappa served at the Editor-in-Chief of PAMI. He is a Golden Core Member of the IEEE Computer Society, served as a Distinguished Lecturer of the IEEE Signal Processing Society and as the President of IEEE Biometrics Council. He is a Fellow of IEEE, IAPR, OSA, AAAS, ACM and AAAI and holds four patents.

Jianxin Wu received his BS and MS degrees in computer science from Nanjing University, and his PhD degree in computer science from the Georgia Institute of Technology. He is currently a professor in the Department of Computer Science and Technology at Nanjing University, China, and is associated with the National Key Laboratory for Novel Software Technology, China. He was an assistant professor in the Nanyang Technological University, Singapore. His research interests are computer vision and machine learning. He has served as an area chair for ICCV and ACCV.

Abstract: Convolution Neural Networks (ConvNets) have successfully improved the recognition performance for various facial characteristics such as age, head pose, gender and identity. A large labeled training set is one of the most important factors for its success. However, it is difficult to collect sufficient and complete training images in some domains such as age and head pose estimation, where the image labels are usually ordered numbers. Fortunately, there is a correlation among neighboring labels, which makes these tasks different from traditional classification. Based on this fact, we convert the label of each image into a discrete label distribution. In this paper, we propose a novel deep label distribution learning (DLDL) framework by minimizing a Kullback-Leibler divergence between the predicted and groundtruth label distributions. DLDL effectively utilizes the correlation information among neighboring labels in both feature learning and classifier learning. Experimental results show that the proposed approach produces significantly better results than state-of-the-art methods for age estimation and head pose estimation, and is particular suitable when the training set is small.

Abstract: Touchless hand gesture recognition systems are becoming important in automotive user interfaces as they improve safety and comfort. Various computer vision algorithms have employed color and depth cameras for hand gesture recognition, but robust classification of gestures from different subjects performed under widely varying lighting conditions is still challenging. We propose an algorithm for dynamic hand gesture recognition that utilizes multiple sensors: depth, intensity and radar with a 3D convolutional neural networks (CNN)-based classifier. We interleave the multiple channels to build normalized spatio-temporal gesture volumes and train gesture classifiers on CUDA-capable NVIDIA GPUs using Theano. To reduce potential overfitting with limited training data and to improve the generalization capability of the classifier, we propose an effective online and offline spatio-temporal data augmentation method. Our algorithm results in the best performance on two challenging multi-modal dynamic hand gesture datasets compared to the existing approaches.

Larry S. Davis is a professor of computer science and director of the Center for Automation Research (CfAR). His research focuses on object/action recognition/scene analysis, event and modeling recognition, image and video databases, tracking, human movement modeling, 3-D human motion capture, and camera networks. Davis is also affiliated with the Computer Vision Laboratory in CfAR. He served as chair of the Department of Computer Science from 1999 to 2012. He received his doctorate from the University of Maryland in 1976. He was named an IAPR Fellow, an IEEE Fellow, and ACM Fellow.