3 papers
cs.CV2025
Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
Qing Jiang, Xingyu Chen, Zhaoyang Zeng +2
Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning i…
cs.CV2025
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Tianhe Ren, Yihao Chen, Qing Jiang +17
In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X…
cs.CV2025
HandOS: 3D Hand Reconstruction in One Stage
Xingyu Chen, Zhuheng Song, Xiaoke Jiang +3
Existing approaches of hand reconstruction predominantly adhere to a multi-stage framework, encompassing detection, left-right classification, and pose estimation. This paradigm in…