AI Paper Atlas

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

Towards Comprehensive Lecture Slides Understanding: Large-scale Dataset and Effective Method

Enming Zhang, Yuzhe Li, Yuliang Liu, Yingying Zhu, Xiang Bai

ICCV 2025 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 1 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 Text Relation Prediction Module (RPH, RAL, pseudo labels) (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 36.3 -> 42.2Improved
add Text Relation Prediction Module (RPH, RAL, pseudo labels) (ablation)SlideParser · LecSlides-370K Lecture Summary (val)METEOR: 26.9 -> 31.3Improved
add weak supervision pseudo labels to RPH+RAL (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 37.5 -> 42.2Improved
learn relations with RPH under weak supervision instead of feeding pseudo labels directly to RAL (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 41.8 -> 42.2Improved
use DL-Cluster pseudo labels instead of Kmeans k=3 (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 40.9 -> 42.2Improved
use DL-Cluster pseudo labels instead of DBSCAN (ablation)SlideParser · LecSlides-370K Lecture Summary (val)METEOR: 30.6 -> 31.3Improved
use DL-Cluster instead of HAC (n=3) (ablation)SlideParser · LecSlides-370K Lecture Summary (val)METEOR: 30.1 -> 31.3Improved
add spatial relation to semantic-only DL-Cluster (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 38.3 -> 42.2Improved
add semantic relation to spatial-only DL-Cluster (ablation)SlideParser · LecSlides-370K Lecture Summary (val)ROUGE-1: 41.4 -> 42.2Improved
pretrain on LecSlides-370K before fine-tuning on SlideVQASlideParser · SlideVQA testEM: 37.5 -> 42.4Improved
pretrain on LecSlides-370K before fine-tuning on SlideVQASlideParser · SlideVQA testF1: 43.9 -> 47.7Improved
use SlideParser over UDOP on lecture summarySlideParser vs UDOP · LecSlides-370K Lecture Summary (test)ROUGE-1: 35.3 -> 41.7Improved

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