# Attend to what I say: Highlighting relevant content on slides

arXiv: https://arxiv.org/abs/2601.10244 · HTML: https://mlsanity.com/paper/2601.10244/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Aligning Subtitles in Sign Language Videos](https://mlsanity.com/paper/2105.02877/) (2021)
- [ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images](https://mlsanity.com/paper/2306.03287/) (2023)
- [Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/2010.11727/) (2020)
- [A Comprehensive Handwritten Paragraph Text Recognition System: LexiconNet](https://mlsanity.com/paper/2205.11018/) (2022)
- [Unsupervised Audio-Visual Lecture Segmentation](https://mlsanity.com/paper/2210.16644/) (2022)

## Built on by (most cited first, 1 of 1)

- [Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media](https://mlsanity.com/paper/2605.05831/) (2026)

## Abstract (arXiv)

Imagine sitting in a presentation, trying to follow the speaker while simultaneously scanning the slides for relevant information. While the entire slide is visible, identifying the relevant regions can be challenging. As you focus on one part of the slide, the speaker moves on to a new sentence, leaving you scrambling to catch up visually. This constant back-and-forth creates a disconnect between what is being said and the most important visual elements, making it hard to absorb key details, especially in fast-paced or content-heavy presentations such as conference talks. This requires an understanding of slides, including text, graphics, and layout. We introduce a method that automatically identifies and highlights the most relevant slide regions based on the speaker's narrative. By analyzing spoken content and matching it with textual or graphical elements in the slides, our approach ensures better synchronization between what listeners hear and what they need to attend to. We explore different ways of solving this problem and assess their success and failure cases. Analyzing multimedia documents is emerging as a key requirement for seamless understanding of content-rich videos, such as educational videos and conference talks, by reducing cognitive strain and improving comprehension. Code and dataset are available at: https://github.com/meghamariamkm2002/Slide_Highlight