Skip to content
View ZhangErliCarl's full-sized avatar
5 followers · 2 following

Highlights

  • Pro

Block or report ZhangErliCarl

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
ZhangErliCarl/README.md

👋 Hello, I'm ZHANG Erli!

👤 About me

I am a first-year PhD student at the National University of Singapore 🇸🇬, majoring in Biomedical Engineering. Prior to this, I obtained a Bachelor of Engineering in Computer Science from Nanyang Technological University. My current research interests include AI in Healthcare, Surgical Video Analysis, and Large Multimodal Models.

📖 Publications

Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning

  • Conference: NeurIPS 2024 Workshop
  • Description: Efficient Segment Anything 2 (SAM2) with frame pruning mechanism for real-time surgical video segmentation
  • 📖 Paper

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

  • Conference: CVPR 2024
  • Description: Low-level visual instruction tuning for multi-modality LLMs
  • 📖 Paper

Q-Bench: Multi-Modality Benchmarking

  • Conference: ICLR 2024 (spotlight)
  • Description: A benchmark for multi-modality LLMs on low-level vision and visual quality assessment.
  • 📖 Paper

MaxVQA/MaxWell: Towards Explainable VQA

  • Conference: ACMMM 2023 (oral)
  • Description: Introduced a 16-dimensional VQA Dataset and Method for a more explainable VQA.
  • 📖 Paper

DOVER: NR-VQA Method

  • Conference: ICCV 2023
  • Description: A state-of-the-art NR-VQA method that predicts disentangled aesthetic and technical quality.
  • 📖 Paper

📬 Contact Me

Pinned Loading

  1. DOVER DOVER Public

    Forked from VQAssessment/DOVER

    [ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.

    Jupyter Notebook 1

  2. MaxVQA MaxVQA Public

    Forked from VQAssessment/ExplainableVQA

    [ACMMM, 2023] "Towards Explainable Video Quality Assessment: A Database and a Language-Prompted Approach"

    Python 1

  3. Q-Future/Q-Bench Q-Future/Q-Bench Public

    ①[ICLR2024 Spotlight] (GPT-4V/Gemini-Pro/Qwen-VL-Plus+16 OS MLLMs) A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

    Jupyter Notebook 251 13