3 papers
cs.CV2020
Tamed Warping Network for High-Resolution Semantic Video Segmentation
Songyuan Li, Junyi Feng, Xi Li
Recent approaches for fast semantic video segmentation have reduced redundancy by warping feature maps across adjacent frames, greatly speeding up the inference phase. However, the…
cs.CV2020
Progressive Multi-Stage Learning for Discriminative Tracking
Weichao Li, Xi Li, Omar Elfarouk Bourahla +5
Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging pr…
cs.LG2018
State Distribution-aware Sampling for Deep Q-learning
Weichao Li, Fuxian Huang, Xi Li +2
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample effici…