High quality structured output learning using single-step gradient discriminant analysis – In this paper we propose a novel, efficient method for supervised prediction of large-scale image retrieval. Firstly, we first learn a novel dataset with a large domain of labels and an efficient classifier model to predict future examples. Then, we train the classifier model with a weighted sum of the label weights of past examples. We also propose a novel deep learning based method for learning the label-preserving feature representations, to reduce the memory cost of the classifier. The proposed algorithm requires only $n$ samples in $n$ deep learning models. We evaluate our method on a large-scale set of data.

We present a novel approach to detect large-scale object detection from unlabeled video images. Instead of training a deep convolutional network to learn to detect specific objects, we train a neural network to learn to recognize more salient features from unlabeled videos. Experimental results show that our approach significantly outperforms previous methods on the challenging PASCAL VOC dataset collected from an urban neighborhood.

A study to determine the maximum number of participants in the screening process for the Multi-Person Registration Platform

Robust Learning of Spatial Context-Dependent Kernels

High quality structured output learning using single-step gradient discriminant analysis

Learning to Summarize a Sentence in English and Mandarin

Learning an RGBD Model of a Moving Object using Deep LearningWe present a novel approach to detect large-scale object detection from unlabeled video images. Instead of training a deep convolutional network to learn to detect specific objects, we train a neural network to learn to recognize more salient features from unlabeled videos. Experimental results show that our approach significantly outperforms previous methods on the challenging PASCAL VOC dataset collected from an urban neighborhood.