AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems

Qi Gao, Heng Li, Yixin Zhou, Meixuan Zhou, Jieqiong Chen, Xinyu Chai

AAAI 2026 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sample 1 fps instead of a single middle frame (ablation)Gemini-2.5-Pro · VisAssistAVG score: 2.86 -> 3.30Improved
use FSM keyframes instead of 0.5 fps uniform (ablation)Gemini-2.5-Pro · VisAssistAVG score: 3.13 -> 3.15Improved
use FSM keyframes instead of 0.5 fps uniform (ablation)Qwen2-VL-OCR · VisAssistAVG score: 2.05 -> 2.00Hurt
use FSM keyframes instead of 1 fps (ablation)Qwen2.5-VL · VisAssistAVG score / TFLOPs: 2.37 -> 2.19 AVG; 12.64 -> 6.17 TFLOPsMixed
raise input resolution from 224x224 to 448x448 (ablation)Gemini-2.5-Pro · VisAssistAVG score: 3.20 -> 3.30Improved
raise input resolution from 224x224 to 448x448 (ablation)VideoLLaMA2 · VisAssistAVG score: 1.51 -> 1.67Improved
raise input resolution from 224x224 to 448x448 (ablation)Qwen2.5-VL · VisAssistAVG score: 2.34 -> 2.37Improved
model scale/capability: closed-source models vs open-source video LLMs in zero-shotVisAssist zero-shot · VisAssist (Chinese)Avg score: 1.04 (TimeChat) -> 3.30 (Gemini-pro)Improved
fine-tune open-source models on VisAssist training splitQwen2.5-VL · VisAssist (ZH)avg COR/DO/SU: 2.37 (zero-shot, answer-only GT) -> 1.865 (fine-tuned, answer+suggestion GT)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy