activity
20172023
most citedMulti-level Residual Networks from Dynamical Systems View

66 citations · 163 across the 16 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.RO2017★ 9 cited

Autonomous Mobile Robot Navigation in Uneven and Unstructured Indoor Environments

Chaoqun Wang, Lili Meng, Sizhen She +6

Robots are increasingly operating in indoor environments designed for and shared with people. However, robots working safely and autonomously in uneven and unstructured environment…

cs.CV2017★ 14 cited

Backtracking Regression Forests for Accurate Camera Relocalization

Lili Meng, Jianhui Chen, Frederick Tung +3

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection. Recent…

cs.CV2017★ 2 cited

Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

Lili Meng, Frederick Tung, James J. Little +2

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure and loop closure detection. Recent…

stat.ML2017★ 66 cited

Multi-level Residual Networks from Dynamical Systems View

Bo Chang, Lili Meng, Eldad Haber +2

Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks. However, the theoretical principles…

cs.CV2017★ 15 cited

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization

Frederick Tung, Srikanth Muralidharan, Greg Mori

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the spec…

cs.CV2017★ 10 cited

Learning Person Trajectory Representations for Team Activity Analysis

Nazanin Mehrasa, Yatao Zhong, Frederick Tung +2

Activity analysis in which multiple people interact across a large space is challenging due to the interplay of individual actions and collective group dynamics. We propose an end-…