A contrastive learning-based framework for EEG-image cross-modal alignment and retrieval. Designed for the THINGS-EEG dataset, this project achieves precise retrieval from EEG signals to visual ...
Abstract Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF, have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch training and ...
Python was used as the programming language, PyTorch 2.2.2 was adopted as the deep learning framework, and CUDA 12.8 was used for GPU acceleration. Weed images were annotated using LabelImg, and all ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results