Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection
Xinnan Zhu, Yicheng Zhu, Tixin Chen +2
Temporal action detection aims to locate and classify actions in untrimmed videos. While recent works focus on designing powerful feature processors for pre-trained representations…
cs.CV2024
When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective
Qiqi Zhou, Yichen Zhu
This paper investigates the Neural Tangent Kernel (NTK) to search vision transformers without training. In contrast with the previous observation that NTK-based metrics can effecti…