368 citations · 527 across the 27 of their papers we have counts for
4 papers · 2 filters
All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines
Yuxuan Zhang, Bo Dong, Felix Heide
Existing neural networks for computer vision tasks are vulnerable to adversarial attacks: adding imperceptible perturbations to the input images can fool these methods to make a fa…
TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition
Chuanfei Hu, Weijie Sheng, Bo Dong +1
Recognizing the human emotion automatically from visual characteristics plays a vital role in many intelligent applications. Recently, gait-based emotion recognition, especially ga…
Object Tracking by Jointly Exploiting Frame and Event Domain
Jiqing Zhang, Xin Yang, Yingkai Fu +3
Inspired by the complementarity between conventional frame-based and bio-inspired event-based cameras, we propose a multi-modal based approach to fuse visual cues from the frame- a…
Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking
Jiqing Zhang, Kai Zhao, Bo Dong +4
Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effective…