Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024
Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
Xinyao Li, Yuke Li, Zhekai Du +3
Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VL…
cs.CV2023
HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V
Yuhang Liu, Boyi Sun, Yuke Li +2
To develop the next generation of intelligent LiDARs, we propose a novel framework of parallel LiDARs and construct a hardware prototype in our experimental platform, DAWN (Digital…
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…