PulseAugur
EN
LIVE 07:22:13

New ClearText-Video dataset probes MLLM text-reading in low-quality videos

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced ClearText-Video (CTVid), a new large-scale dataset designed to evaluate how multimodal large language models (MLLMs) handle text-centric video understanding under varying quality conditions. CTVid includes over 4,600 videos with more than 1.6 million human-verified scene-text annotations and 220,000 question-answer pairs in both Chinese and English. The dataset features degraded and restored versions of videos to test text-centric video restoration and multi-quality video question-answering, revealing that visual enhancement does not always improve textual fidelity or reasoning performance for MLLMs. AI

IMPACT This dataset will enable researchers to better understand and improve MLLM performance on real-world, low-quality video data.

RANK_REASON The item describes a new dataset and associated research paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New ClearText-Video dataset probes MLLM text-reading in low-quality videos

How we ranked this

Signal score
23 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new dataset and associated research paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Jinlong Li, Jiaming Ding, Dingfu Lu, Malcolm Hsiu, Chuang Ke, Kangning Yang, Bochen Guan, Lan Fu, Jie Cai, Huiming Sun, Zibo Meng ·

    ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement

    arXiv:2608.28784v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently made strong progress in visual--linguistic understanding. However, their performance on text-centric video reasoning remains highly sensitive to input quality. Real-world user-p…

RELATED ENTITIES

RELATED TOPICS