One paper has been accepted by ACM MM 2025!

Shengli Zhou Lv1

Learn 3D VQA Better with Active Selection and Reannotation

  • Shengli Zhou, Yang Liu, Feng Zheng†
  • Accepted by ACM MM 2025 / Paper (arXiv) / Code (GitHub)
  • To address the negative impact of inevitable improper annotation in 3D Visual Question-Answering and the scarcity of annotations, we propose a multi-turn interactive active learning strategy, combining semantic variance-based data selection with interactive oracle reannotation, enhancing answer quality and reducing training costs.
  • Title: One paper has been accepted by ACM MM 2025!
  • Author: Shengli Zhou
  • Created at : 2025-07-06 01:22:00
  • Updated at : 2025-09-06 07:10:35
  • Link: https://fz-zsl.github.io/ACMMM2025/
  • License: This work is licensed under CC BY-NC-SA 4.0.
On this page
One paper has been accepted by ACM MM 2025!