Dual Contrastive Learning for Unsupervised Image-to-Image Translation

SimDCL：无监督图像到图像翻译的对偶对比学习.

Making the Invisible Visible: Action Recognition Through Walls and Occlusions

RF-Action：使用射频信号进行多人动作识别.

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

通过深度语言理解实现真实文本图像扩散模型.

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

GLIDE：通过文本引导的扩散模型实现真实图像生成与编辑.

Hierarchical Text-Conditional Image Generation with CLIP Latents

通过CLIP隐特征实现层次化文本条件图像生成.

Learning Longterm Representations for Person Re-Identification Using Radio Signals

RF-ReID：使用射频信号学习目标重识别的长期表示.