Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D …

Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver fo…

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output…

Generative VoxelNet : Learning Energy-Based Models for 3D Shape Synthesis and…

3D data that contains rich geometry information of objects and scenes is valuable for understanding 3D physical world. With the recent emergence of large-scale 3D datasets, it becomes increasingly …

Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns

Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or te…

Revisiting Video Saliency Prediction in the Deep Learning Era

Cooperative Training of Descriptor and Generator Networks