Metraipolis › archive › dc_c497c49f55bb
KnowVis: Knowledge-Centric Visual Summarization for Video Lectures — arXiv:2609.03742
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03742
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:41:56.235Z
- SHA-256 of the archived text
176046f2dc60b6023b73804e719ed9bce44e5227ff7792d89adc5a8e7805f504- Stable URL of this page
https://metraipolis.com/documento/dc_c497c49f55bb
How to cite
KnowVis: Knowledge-Centric Visual Summarization for Video Lectures — arXiv:2609.03742 — arXiv (en), https://arxiv.org/abs/2609.03742 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c497c49f55bb (Metraipolis archive dc_c497c49f55bb, sha256 176046f2dc60b6023b73804e719ed9bce44e5227ff7792d89adc5a8e7805f504)
BibTeX
@misc{dcc497c49f55bb,
title = {KnowVis: Knowledge-Centric Visual Summarization for Video Lectures — arXiv:2609.03742},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03742},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c497c49f55bb; sha256 176046f2dc60b6023b73804e719ed9bce44e5227ff7792d89adc5a8e7805f504},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03742. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video lectures are valuable educational resources, but their dense and lengthy formats often overwhelm novice learners. This difficulty stems from a fundamental pedagogical mismatch: while videos deliver transient information linearly, human learning requires constructing interconnected cognitive networks, a task that induces severe cognitive overload for novice learners lacking prior domain knowledge. Existing video summarization methods fail to resolve this mismatch, as they primarily produce text-heavy, linear condensations that still demand high cognitive effort. To bridge this gap, we propose KnowVis, a framework that transforms linear video lectures into pedagogically grounded visual narratives. KnowVis first extracts a detailed concept map from multimodal video content to identify important and challenging threshold concepts, then constructs structured knowledge units, and finally synthesizes engaging visual summaries. Alongside the framework, we introduce a curated dataset of 125 educational videos across 10 academic disciplines, paired with 1,079 generated visual summaries. Extensive automated evaluations and a human study demonstrate that, compared to state-of-the-art baselines, KnowVis generates more accurate and clear visuals that successfully reduce cognitive load and significantly improve student learning effectiveness and knowledge retention. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.03742 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T01:11:43.599Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).