activity
20182023
most citedA Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking

6 citations · 16 across the 10 of their papers we have counts for

collaborators

16 papers

cs.CV2023

Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline

Zhigang Chang, Weitai Hu, Qing Yang +1

In dyadic speaker-listener interactions, the listener's head reactions along with the speaker's head movements, constitute an important non-verbal semantic expression together. The…

cs.CV2023★ 5 cited

Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving

Zijian Zhu, Yichi Zhang, Hai Chen +5

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the…

cs.CV2023★ 2 cited

To Make Yourself Invisible with Adversarial Semantic Contours

Yichi Zhang, Zijian Zhu, Hang Su +4

Modern object detectors are vulnerable to adversarial examples, which may bring risks to real-world applications. The sparse attack is an important task which, compared with the po…

cs.CV2023★ 6 cited

A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking

Chang Liu, Yinpeng Dong, Wenzhao Xiang +7

The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in th…

cs.CV2023

Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain

Chang Liu, Wenzhao Xiang, Yuan He +3

Deep neural networks (DNNs) may suffer from significantly degenerated performance when the training and test data are of different underlying distributions. Despite the importance…

cs.CV2021

Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification

Zhigang Chang, Zhao Yang, Yongbiao Chen +2

ideo-based person re-identification (Re-ID) aims to match person images in video sequences captured by disjoint surveillance cameras. Traditional video-based person Re-ID methods f…