12 citations · 22 across the 6 of their papers we have counts for
6 papers
Diverse Policies Converge in Reward-free Markov Decision Processe
Fanqi Lin, Shiyu Huang, Weiwei Tu
Reinforcement learning has achieved great success in many decision-making tasks, and traditional reinforcement learning algorithms are mainly designed for obtaining a single optima…
TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play
Fanqi Lin, Shiyu Huang, Tim Pearce +2
Multi-agent football poses an unsolved challenge in AI research. Existing work has focused on tackling simplified scenarios of the game, or else leveraging expert demonstrations. I…
Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation
Fanqing Lin, Tony Martinez
Color-based two-hand 3D pose estimation in the global coordinate system is essential in many applications. However, there are very few datasets dedicated to this task and no existi…
Generalizing Interactive Backpropagating Refinement for Dense Prediction
Fanqing Lin, Brian Price, Tony Martinez
As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation o…
Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection
Fanqing Lin, Brian Price, Tony Martinez
Hand segmentation and detection in truly unconstrained RGB-based settings is important for many applications. However, existing datasets are far from sufficient in terms of size an…
Two-hand Global 3D Pose Estimation Using Monocular RGB
Fanqing Lin, Connor Wilhelm, Tony Martinez
We tackle the challenging task of estimating global 3D joint locations for both hands via only monocular RGB input images. We propose a novel multi-stage convolutional neural netwo…