ARTE Group

ICLR 2025

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

A visual-centric perspective for improving CLIP spatial understanding

Congpei Qiu Yanhao Wu Wei Ke Xiuxiu Bai Tong Zhang

ICLR · 2025

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective teaser image

Video Gallery

Citation

@misc{qiu2025refiningclipsspatialawareness,
      title={Refining CLIP's Spatial Awareness: A Visual-Centric Perspective},
      author={Congpei Qiu and Yanhao Wu and Wei Ke and Xiuxiu Bai and Tong Zhang},
      year={2025},
      eprint={2504.02328},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.02328},
}