Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking
Ben Kang, Xin Chen, Jie Zhao +3
Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constra…
cs.CV2025
Efficient Motion Prompt Learning for Robust Visual Tracking
Jie Zhao, Xin Chen, Yongsheng Yuan +3
Due to the challenges of processing temporal information, most trackers depend solely on visual discriminability and overlook the unique temporal coherence of video data. In this p…