5 papers · 1 filter
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Bin Yan, Houwen Peng, Kan Wu +3
Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployment…
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
Bin Yan, Xinyu Zhang, Dong Wang +2
Visual object tracking aims to precisely estimate the bounding box for the given target, which is a challenging problem due to factors such as deformation and occlusion. Many recen…
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
Bin Yan, Dong Wang, Huchuan Lu +1
In recent years, the multiple-stage strategy has become a popular trend for visual tracking. This strategy first utilizes a base tracker to coarsely locate the target and then expl…
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
Bin Yan, Dong Wang, Huchuan Lu +1
Adversarial attack of CNN aims at deceiving models to misbehave by adding imperceptible perturbations to images. This feature facilitates to understand neural networks deeply and t…
'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking
Bin Yan, Haojie Zhao, Dong Wang +2
Compared with traditional short-term tracking, long-term tracking poses more challenges and is much closer to realistic applications. However, few works have been done and their pe…