activity
20182022
most citedReal-Time Semantic Segmentation via Multiply Spatial Fusion Network

45 citations · 133 across the 14 of their papers we have counts for

collaborators

22 papers

cs.CV20224 cited

Jitter Does Matter: Adapting Gaze Estimation to New Domains

Ruicong Liu, Yiwei Bao, Mingjie Xu +3

Deep neural networks have demonstrated superior performance on appearance-based gaze estimation tasks. However, due to variations in person, illuminations, and background, performa…

cs.CV20222 cited

Discriminative feature encoding for intrinsic image decomposition

Zongji Wang, Yunfei Liu, Feng Lu

Intrinsic image decomposition is an important and long-standing computer vision problem. Given an input image, recovering the physical scene properties is ill-posed. Several physic…

cs.CV2021

Separating Content and Style for Unsupervised Image-to-Image Translation

Yunfei Liu, Haofei Wang, Yang Yue +1

Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content c…

cs.CV2021

Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation

Yunfei Liu, Ruicong Liu, Haofei Wang +1

Deep neural networks have significantly improved appearance-based gaze estimation accuracy. However, it still suffers from unsatisfactory performance when generalizing the trained…

cs.CV20211 cited

Gaze Estimation using Transformer

Yihua Cheng, Feng Lu

Recent work has proven the effectiveness of transformers in many computer vision tasks. However, the performance of transformers in gaze estimation is still unexplored. In this pap…

cs.CV20212 cited

Vulnerability of Appearance-based Gaze Estimation

Mingjie Xu, Haofei Wang, Yunfei Liu +1

Appearance-based gaze estimation has achieved significant improvement by using deep learning. However, many deep learning-based methods suffer from the vulnerability property, i.e.…