← Search

Pablo Zinemanas

2 accepted papers

2023

Flowgrad: Using Motion for Visual Sound Source Localization

ICASSP 2023accepted

Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner and, by design, excludes temporal information present in videos. While it proves to be effective for widely used benchmark datasets, the method falls short for cha…

Cited by 0SourceScholar
2022

Urban Sound & Sight: Dataset And Benchmark For Audio-Visual Urban Scene Understanding

ICASSP 2022accepted

Automatic audio-visual urban traffic understanding is a growing area of research with many potential applications of value to industry, academia, and the public sector. Yet, the lack of well-curated resources for training and evaluating models to research in this area hinders their development. To a…

Cited by 16SourceScholar