Skip to content

Resources

Code

MULTIFLOW on Github:

https://github.com/daedalusLAB

Datasets

Ariadna speech-gesture database

Extracted from UCLA’s NewsScape Library of Television News. How to access NewsScape.

Latest version (Nov 2023): parquet and videos (295MB)

Questions? Ask Cristobal Pagán: cpcanovas@um.es 

CREATIME speech-gesture database

Extracted from UCLA’s NewsScape Library of Television News. How to access NewsScape.

Latest version (Jan 2020): .xls (1,2 MB). Sample of variety of speakers: .xls(23KB). 

Questions? Ask Daniel Alcaraz: daniel.alcaraz@um.es.

PoetiCog: an annotated corpus of figurative language in lyric poetry

About 2 million words of English, Spanish, and Greek lyric poetry. We are expanding the collection. Compiled and searchable with SketchEngine. Semantic annotation in progress

For more info, ask Rosa Illán: mariarosario.illan@um.es.

Talks

Cristóbal Pagán Cánovas

Modeling the multimodal flow: gesture and semantics. Case Western Reserve University, College of Arts and Sciences, Data Science Colloquium. 28 April 2021.

Cristóbal Pagán Cánovas

The cross-cultural patterns of poetic performance in oral traditions: multimodality, communication, and cognition. Pleary lecture, International Conference on Intercultural Multimodal Communication. Hunan Normal U. Changsha, 12-13 December 2020.

Cristóbal Pagán Cánovas

The cognitive, multimodal, and quantitative turns: Opportunities for collaboration. Labex GRÉAM, University of Strasbourg. Multidisciplinary Contributions to Musicology: Questions and Challenges. Strasbourg, 2 February 2018.

Posters