7 papers
State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend
Fei Cui, Jiaojiao Fang, Xiaojiang Wu +4
Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic vi…
Landmark Guided Active Exploration with State-specific Balance Coefficient
Fei Cui, Jiaojiao Fang, Mengke Yang +1
Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results…
Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D
Jiaojiao Fang, Guizhong Liu
Self-supervised learning of depth and ego-motion from unlabeled monocular video has acquired promising results and drawn extensive attention. Most existing methods jointly train th…
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos
Jiaojiao Fang, Guizhong Liu
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. Howeve…
Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
Lingtao Zhou, Jiaojiao Fang, Guizhong Liu
Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch…
Object Viewpoint Classification Based 3D Bounding Box Estimation for Autonomous Vehicles
Zhou Lingtao, Fang Jiaojiao, Liu Guizhong
3D object detection is one of the most important tasks for the perception systems of autonomous vehicles. With the significant success in the field of 2D object detection, several…