most citedConservative Wasserstein Training for Pose Estimation

16 citations · 28 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20207 cited

Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving

Xiaofeng Liu, Yimeng Zhang, Xiongchang Liu +3

Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progr…

cs.CV201916 cited

Conservative Wasserstein Training for Pose Estimation

Xiaofeng Liu, Yang Zou, Tong Che +4

This paper targets the task with discrete and periodic class labels ( pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or regres…

cs.CV2019

Attention Control with Metric Learning Alignment for Image Set-based Recognition

Xiaofeng Liu, Zhenhua Guo, Jane You +1

This paper considers the problem of image set-based face verification and identification. Unlike traditional single sample (an image or a video) setting, this situation assumes the…

cs.CV2019

Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition

Xiaofeng Liu, Zhenhua Guo, Site Li +4

We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images. We use feature restructuring to exploit the c…

cs.CV2019

Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets

Xiaofeng Liu, B. V. K Vijaya Kumar, Chao Yang +2

This paper targets the problem of image set-based face verification and identification. Unlike traditional single media (an image or video) setting, we encounter a set of heterogen…

eess.IV2019

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

Mu Li, Kede Ma, Jane You +2

Precise estimation of the probabilistic structure of natural images plays an essential role in image compression. Despite the recent remarkable success of end-to-end optimized imag…