3 papers
cs.CV2026
Drift-Resilient Temporal Priors for Visual Tracking
Yuqing Huang, Liting Lin, Weijun Zhuang +2
Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In…
cs.CV2026
Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation
Yuqing Huang, Guotian Zeng, Zhenqiao Yuan +4
Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To…
cs.CV2026
Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining
Weijun Zhuang, Yuqing Huang, Weikang Meng +5
Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked vi…