3 papers
cs.CV2026
Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
Zhilin Zhu, Yabin Wang, Zhiheng Ma +3
Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a…
cs.CV2026
Thermal-Only Crowd Counting with Deployment-Time Privacy Protection
Yifei Qian, Zhongliang Guo, Chun Tong Lei +4
While RGB-Thermal crowd counting has shown promise, the paradigm faces critical limitations: RGB data raises privacy concerns in public surveillance, and multi-modal misalignment d…
cs.CV2025
T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
Yifei Qian, Zhongliang Guo, Bowen Deng +5
Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP…