AI Paper Atlas

Research map / Video / Video-language understanding

ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

Zhentao Guo, Chen Duan, Tongkun Guan, Zining Wang, Kai zhou, Pengfei Yan

ECCV 2026 · Video › Video-language understanding · approach: Video question answering · 3 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
add ViTexQA training data (plain SFT) to Qwen3-VLQwen3-VL-8B · ViTexQAROUGE-L: 66.7 -> 76.9 (+10.2)Improved
add ViTexQA training data to MiniCPM-V4.5MiniCPM-V4.5 · ViTexQAROUGE-L: 70.1 -> 77.2 (+7.1)Improved
add ViTexQA training data to Qwen3-VL (out-of-domain MME-VideoOCR)Qwen3-VL-8B · MME-VideoOCRscore: 68.5 -> 74.3 (+5.8)Improved
add ViTexQA training data to Qwen3-VL (single-image TextVQA)Qwen3-VL-8B · TextVQAaccuracy: 84.5 -> 84.6 (+0.1)No clear effect
add ViTexQA training data to MiniCPM-V4.5 (Video-MME)MiniCPM-V4.5 · Video-MMEscore: 68.8 -> 70.6 (+1.6)Hurt
add CoT-guided SFT on top of ViTexQA data (ablation)FrameThinker · ViTexQAROUGE-L: 76.3 -> 81.4 (5.1% over No.(2))Improved
add temporally-grounded RL after CoT-SFT (ablation)FrameThinker · ViTexQAROUGE-L: 81.4 -> 83.5Improved
add temporally-grounded RL after CoT-SFT (ablation)FrameThinker · MME-VideoOCRscore: 85.3 -> 88.1Improved
add CoT-guided SFT and RL plus ViTexQA data versus the baseline (ablation)FrameThinker · ViTexQAROUGE-L: 73.5 -> 83.5 (+10.0)Improved
add ViTexQA data only (no CoT-SFT, no RL) to the baseline FrameThinker model (ablation)FrameThinker · ViTexQAROUGE-L: 73.5 -> 76.3 (+2.8)Improved
increase input resolution (ablation)FrameThinker · ViTexQAROUGE-LNo clear effect
increase number of input frames (ablation)FrameThinker · ViTexQAROUGE-LImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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