Jaeseong Lee*, Yeeun Choi*, Heechan Choi*, Hanjung Kim, Seon Joo Kim
CVPR 2025 Workshop Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo 2) accepted!
To simplify deployment and ensure consistent environments, we recommend using the official Qwen2.5-VL Docker image.
📝 Reference: Qwen2.5-VL GitHub Repository
docker run --gpus all --ipc=host --network=host --rm --name qwen2.5 -it qwenllm/qwenvl:2.5-cu121 bashThis launches a container with all necessary dependencies pre-installed, based on Qwen2.5-VL's official setup.
Clone this repo and download datasets as follows:
# Clone repository
git clone https://github.com/yeencye/ECP.gitInside GUI-grounding/, download the ScreenSpot-Pro dataset
Inside MLLM-perception/, download the HR-Bench dataset
Run the following script to generate candidate regions:
bash GUI-grounding/EC.shThis will save cropped regions and intermediate JSONs under ./EC_output.
Run the following script to refine the bounding boxes using Qwen2.5VL or OS-Atlas:
bash GUI-grounding/P.shThis will run inference on the cropped regions and save final prediction results under ./P_output.
