Hi there 👋

• 🔭 My academic pursuit in Computer Vision and Deep Learning initially centered around video understanding, with a focus on action recognition and detection. Later, I explored the realm of Self-supervised Learning, studying how machines can learn autonomously from inherent data structures. Recently, my interest has gravitated towards the intersection of 3D/4D World Reconstruction and Understanding. My primary research now seeks to reconstruct/generate structured/semantic 3D/4D world for intelligent interactions, bridging 3D/4D construction with semantic comprehension. The ultimate aim is to harness these models to facilitate seamless communication between machines, humans, and their environments.
• 📫 How to reach me: [email protected]