activity
20172022
most citedEvent2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection

6 citations · 12 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2021

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

Yuhang Wu, Tengteng Huang, Haotian Yao +5

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a u…

cs.CV2020★ 1 cited

Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions

Yuhang Wu, Sunpreet S. Arora, Yanhong Wu +1

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize a…

cs.CV2020★ 2 cited

Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study

Dinh-Luan Nguyen, Sunpreet S. Arora, Yuhang Wu +1

Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability…

cs.CV2019

Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition

Yuhang Wu, Ioannis A. Kakadiaris

Concatenation of the deep network representations extracted from different facial patches helps to improve face recognition performance. However, the concatenated facial template i…

cs.CV2018

Convolutional Point-set Representation: A Convolutional Bridge Between a Densely Annotated Image and 3D Face Alignment

Yuhang Wu, Le Anh Vu Ha, Xiang Xu +1

We present a robust method for estimating the facial pose and shape information from a densely annotated facial image. The method relies on Convolutional Point-set Representation (…

cs.CV2017

Facial 3D Model Registration Under Occlusions With SensiblePoints-based Reinforced Hypothesis Refinement

Yuhang Wu, Ioannis A. Kakadiaris

Registering a 3D facial model to a 2D image under occlusion is difficult. First, not all of the detected facial landmarks are accurate under occlusions. Second, the number of relia…