2 papers
cs.CV2025
Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment
Xiaowei Bi, Zheyuan Xu
While multi-modal learning has advanced significantly, current approaches often create inconsistencies in representation and reasoning of different modalities. We propose UMaT, a t…
cs.CV2025
Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networks
Yuhui Jin, Yaqiong Zhang, Zheyuan Xu +2
In the field of computer vision, 6D object detection and pose estimation are critical for applications such as robotics, augmented reality, and autonomous driving. Traditional meth…