Wenxuan Xie

We investigate weakly-supervised image parsing, i.e., how to propagate class labels from images to regions given an affinity graph of regions. Expand

We address the problem of weakly-supervised image parsing, whose aim is to automatically determine the class labels of image regions given image-level labels only. Expand

We design the learned updater based on recurrent neural networks (RNNs) and demonstrate its application in a template-based tracker and a correlation filter-based Tracker. Expand

We propose a cross-view feature learning (CVFL) framework to handle the problem of social image analysis effectively and efficiently. Expand

This work was done when Hao Luo was an intern at Microsoft Research Asia. Expand

We design the learned updater based on recurrent neural networks and demonstrate its application in a template-based tracker and a correlation filter-based Tracker. Expand

We investigate an image classification task where training images come along with tags, but only a subset being labeled, and the goal is to predict the class label of test images without tags. Expand

We investigate an image classification task where the training images come along with tags, but only a subset being labeled, and the goal is to predict the class label of test images without tags. Expand

In this paper, we present a cross-domain framework named TFTNet, which takes time-frequency spectrogram as input and produces time-domain waveform as output. Expand