Scientific talks range from conference presentations to lectures and documentaries. Even though some formats have high-grade content, such as lectures, their presentation is not always the most appealing. On the other hand, documentaries and other entertainment-driven programs can present consolidated information benefiting from aesthetically assured visual and audible effects. Motivated by these aspects, we illustrate the topics of a physics lecture through the use of documentaries. Our main concerns are the process of content selection and coherence aspects. The creation process uses a summarized transcript of a physics lecture to select topic-related content from a collection of documentaries. The issue of coherence is addressed as a consequence of the content selection process, as well as by means of video composition techniques via content organization.
Video Summaries for Science Talks
April 19, 2016
1:00 pm
Paulo Figueiredo
Paulo Figueiredo received both his MSc (2015) and BSc (2013) degree in Information Systems and Computer Engineering from Instituto Superior Técnico (IST), Lisbon, Portugal. His MSc thesis, entitled “Video Summaries for Science Talks”, was done in collaboration with the Spoken Language Systems (L2F) of INESC-ID advised by professor David Martins de Matos and Ricardo Ribeiro. Recently, he published “Summarization of films and documentaries based on subtitles and scripts” in Elsevier’s Pattern Recognition Letters.L2FSeminários
Últimos seminários
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
June 17, 2025Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Speech as a Biomarker for Disease Detection
May 20, 2025Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong…
Enhancing Uncertainty Estimation in Neural Networks
May 6, 2025Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this presentation, I will present…
Improving Evaluation Metrics for Vision-and-Language Models
April 22, 2025Evaluating image captions is essential for ensuring both linguistic fluency and accurate semantic alignment with visual content. While reference-free metrics…