Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
SELECT: Detecting Label Errors in Real-world Scene Text Data
Wenjun Liu, Qian Wu, Yifeng Hu +1
We introduce SELECT (Scene tExt Label Errors deteCTion), a novel approach that leverages multi-modal training to detect label errors in real-world scene text datasets. Utilizing an…
cs.CV2024
HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition
Qian Wu, Ruoxuan Cui, Yuke Li +1
Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the e…
cs.CV2023
Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval
Rui Deng, Qian Wu, Yuke Li +1
Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency…