Du Tran

Du Tran is a research scientist at Facebook AI. He graduated with a Ph.D. in computer science from Dartmouth College and an M.S. in computer science from University of Illinois at Urbana-Champaign. Before coming to Dartmouth, Du was a research staff at Nanyang Technological University. Du's research interests are computer vision, machine learning and computer graphics, with specific interests in video understanding, representation learning, and vision and language. Du is a recipient of a Vietnam Education Foundation Fellowship in 2006 and a Dartmouth Presidential Fellowship in 2012.

Du's Publications

May 19, 2020

RESEARCH

FASTER Recurrent Networks for Efficient Video Classification

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at…

Linchao Zhu, Du Tran, Laura Sevilla-Lara, Yi Yang, Matt Feiszli, Heng Wang

May 19, 2020

May 19, 2020

RESEARCH

Video Classification with Channel-Separated Convolutional Networks

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the agent’s behavior policy from…

Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli

May 19, 2020

May 19, 2020

RESEARCH

DistInit: Learning Video Representations Without a Single Labeled Video

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models has not been able to keep up with the ever increasing depth and sophistication of these networks. In this work…

Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan

May 19, 2020