dc.contributor | Fuentes Magdalena, New York University, New York, NY | |
dc.contributor | Steers Bea, New York University, New York, NY | |
dc.contributor | Zinemanas Pablo, Universitat Pompeu Fabra, Barcelona, Spain | |
dc.contributor | Rocamora Martín, Universidad de la República (Uruguay). Facultad de Ingeniería. | |
dc.contributor | Bondi Luca, Bosch Research, Pittsburgh, PA, USA | |
dc.contributor | Wilkins Julia, New York University, New York, NY | |
dc.contributor | Shi Qianyi, New York University, New York, NY | |
dc.contributor | Hou Yao, New York University, New York, NY | |
dc.contributor | Das Samarjit, Bosch Research, Pittsburgh, PA, USA | |
dc.contributor | Serra Xavier, Universitat Pompeu Fabra, Barcelona, Spain | |
dc.contributor | Bello Juan Pablo, New York University, New York, NY | |
dc.creator | Fuentes, Magdalena | |
dc.creator | Steers, Bea | |
dc.creator | Zinemanas, Pablo | |
dc.creator | Rocamora, Martín | |
dc.creator | Bondi, Luca | |
dc.creator | Wilkins, Julia | |
dc.creator | Shi, Qianyi | |
dc.creator | Hou, Yao | |
dc.creator | Das, Samarjit | |
dc.creator | Serra, Xavier | |
dc.creator | Bello, Juan Pablo | |
dc.date.accessioned | 2022-05-03T12:01:35Z | |
dc.date.accessioned | 2022-10-28T20:21:40Z | |
dc.date.available | 2022-05-03T12:01:35Z | |
dc.date.available | 2022-10-28T20:21:40Z | |
dc.date.created | 2022-05-03T12:01:35Z | |
dc.date.issued | 2022 | |
dc.identifier | Fuentes, M., Steers, B., Zinemanas, P. y otros. Urban sound & sight : Dataset and benchmark for audio-visual urban scene understanding [en línea]. EN: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 23-27 may, pp 141-145. Piscataway, NJ : IEEE, 2022. DOI 10.1109/ICASSP43922.2022.9747644 | |
dc.identifier | https://ieeexplore.ieee.org/document/9747644 | |
dc.identifier | https://hdl.handle.net/20.500.12008/31397 | |
dc.identifier | 10.1109/ICASSP43922.2022.9747644 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/4985287 | |
dc.description.abstract | 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 address this we present a curated audio-visual dataset, Urban Sound & Sight (Urbansas), developed for investigating the detection and localization of sounding vehicles in the wild. Urbansas consists of 12 hours of unlabeled data along with 3 hours of manually annotated data, including bounding boxes with classes and unique id of vehicles, and strong audio labels featuring vehicle types and indicating off-screen sounds. We discuss the challenges presented by the dataset and how to use its annotations for the localization of vehicles in the wild through audio models. | |
dc.language | en | |
dc.publisher | IEEE | |
dc.relation | ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 23-27 may 2022, pp. 141-145. | |
dc.rights | Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) | |
dc.rights | Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014) | |
dc.subject | Location awareness | |
dc.subject | Training | |
dc.subject | Industries | |
dc.subject | Annotations | |
dc.subject | Conferences | |
dc.subject | Signal processing | |
dc.subject | Benchmark testing | |
dc.subject | Audio-visual | |
dc.subject | Urban research | |
dc.subject | Traffic | |
dc.subject | Dataset | |
dc.title | Urban sound & sight : Dataset and benchmark for audio-visual urban scene understanding | |
dc.type | Ponencia | |