Skip to content
View happy-hsy's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
  • University of Surrey
  • London
  • 09:18 (UTC)

Highlights

  • Pro

Block or report happy-hsy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
happy-hsy/README.md

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: haosen.yang.6@gmail.com

Pinned Loading

  1. BCNet BCNet Public

    【AAAI 2022】Temporal Action Proposal Generation with Background Constraint

    Python 18

  2. MotionMAE MotionMAE Public

    Self-Supervised Video Representation Learning with Motion-Aware Masked Autoencoders

    23 1

  3. Surrey-UP-Lab/RegionSpot Surrey-UP-Lab/RegionSpot Public

    Recognize Any Regions

    Python 118 4

  4. Surrey-UP-Lab/GS-LPM Surrey-UP-Lab/GS-LPM Public

    Localized Gaussian Point Management

    Python 60 2