Heng Wang

Heng is a Research Scientist at Facebook AI. His research interests range from low-level vision to high-level vision with a focus on video understanding. You can find more detailed information on Heng's homepage.

Heng's Publications

April 07, 2020

RESEARCH

COMPUTER VISION

Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video…

Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

Leveraging the Present to Anticipate the Future in Videos

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper we…

Antoine Miech, Ivan Laptev, Josef Sivic, Heng Wang, Lorenzo Torresani, Du Tran,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

A Closer Look at Spatiotemporal Convolutions for Action Recognition

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have…

Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri,

April 07, 2020