Skip to content
View zhousheng97's full-sized avatar
🐢
Focusing
🐢
Focusing
17 followers · 10 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report zhousheng97

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
zhousheng97/README.md

Hi there 👋

  • 👩 I’m Sheng, a PhD student from China, currently studying as a visiting student at the National University of Singapore.
  • 🧐 My focus is multimedia learning, especially VQA, and I’m currently exploring multimodal LLMs.
  • 💬 As an ENFJ-A, I thrive on meaningful collaboration and communication.
  • 📫 You can reach me at [email protected]—let’s connect!

Pinned Loading

  1. EgoTextVQA Public

    [CVPR 2025] 🌟🌟 EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering

    Python 26

  2. ViTXT-GQA Public

    ✨✨ Scene-Text Grounding for Text-Based Video Question Answering (arxiv)

    Python 14 1

  3. Awesome-MLLM-TextVQA Public

    ✨✨Latest Research on Multimodal Large Language Models on Scene-Text VQA Tasks

    8

  4. GPIN Public

    Graph Pooling Inference Network for Text-based VQA (ACM TOMM'2024)

    Python 3

  5. SSGN Public

    Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA (IEEE TIP'2023)

    Python 4

326 contributions in the last year

Contribution Graph
Day of Week April May June July August September October November December January February March
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Learn how we count contributions
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Activity overview

Contributed to zhousheng97/zhousheng97.github.io, zhousheng97/EgoTextVQA, zhousheng97/EgoTextVQA_page and 11 other repositories
Loading A graph representing zhousheng97's contributions from April 07, 2024 to April 08, 2025. The contributions are 98% commits, 2% issues, 0% pull requests, 0% code review.   Code review 2% Issues   Pull requests 98% Commits

Contribution activity

April 2025

Created 1 commit in 1 repository

Created an issue in LLaVA-VL/LLaVA-NeXT that received 2 comments

For LLaVA-Video-Qwen2-7B, are the results of video inference and multi-frame inference consistent?

Hello, has anyone tested llava-video-qwen2-7b? Is there any difference in the results for the same video content, but only the difference in multi-…

2 comments
Loading