Dengqing Yang — accepted AI-conference papers

2026

Generalizable Structure-Aware Keypoint Correspondence for Category-Unified 3D Single Object Tracking

Jie Xiao, Yinchao Ma, Yuyang Tang, Dengqing Yang, Jianpeng Yang, Xu Zhou +3

CVPR 2026

3D single object tracking (SOT) in point clouds is essential for real-world 3D perception, yet it remains challenging due to data sparsity and large variations in scale and structure across diverse object categories. Most existing methods rely on a category-specific paradigm that trains separate mod

Cited by 0 Source ↗Scholar ↗

2026

Learning Generalized Trackers with Elastic Token Budgets

Yinchao Ma, Jianpeng Yang, Yuyang Tang, Jie Xiao, Dengqing Yang, Tianzhu Zhang

ICML 2026poster

Visual tracking aims to estimate target states in video sequences, with applications spanning diverse computational requirements. Recent methods optimize trackers using manually pruned image tokens with a fixed budget to reduce computational costs. However, these trackers, once trained, are constrai…

Cited by 0 Source ↗Scholar ↗