Skip to content
View xin-ran-w's full-sized avatar
🔬
brain storm
🔬
brain storm
17 followers · 41 following

Achievements

Achievement: StarstruckAchievement: Pull Shark

Achievements

Achievement: StarstruckAchievement: Pull Shark

Organizations

@PRIS-CV

Block or report xin-ran-w

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
xin-ran-w/README.md

Hi there 👋

  • 🎓 I'm currently pursuing a PhD in the field of multimodal learning.
  • 🔭 I’m currently working on expressing visual content using language (e.g., image captioning, object description).
  • 🌱 I’m looking to collaborate on using high-quality captions to train a diffusion / auto-regressive generation model to generate high-quality visual content (video/image/3D model).
  • 📫 How to reach me: [email protected].

Pinned Loading

  1. PRIS-CV/CineTechBench PRIS-CV/CineTechBench Public

    A Benchmark for Cinematographic Technique Understanding and Generation

    Python 23

  2. CapAgent CapAgent Public

    From Simple to Professional - A Combinatorial Controllable Image Captioning Agent

    Python 7 1

  3. PRIS-CV/ControllableObjectDescription PRIS-CV/ControllableObjectDescription Public

    A training-free pipeline to control dimension details in object description.

    Python 5 1

  4. Caption2SceneGraph Caption2SceneGraph Public

    A parser tool using large language model and vision experts to parse the input caption into a scene graph

    Python