no code implementations • 29 Jun 2021 • Manuel Sarmiento Calderó, David Varas, Elisenda Bou-Balust
Research in action detection has grown in the recentyears, as it plays a key role in video understanding.
no code implementations • 9 Jun 2020 • Carlos Roig, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust
The results showcase an improvement of 2. 63 and 3. 29 in Recall@1 with respect to MultiSimilarity and Proxy-Anchor Loss respectively, proving that our method outperforms the state-of-the-art of Metric Learning in noisy labeling conditions.
no code implementations • 12 May 2020 • Carlos Roig, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust
This paper presents a system towards the generation of multi-label datasets from web data in an unsupervised manner.
no code implementations • 1 Nov 2019 • Marc Maceira, David Varas, Josep-Ramon Morros, JavierRuiz-Hidalgo, Ferran Marques
Depth data has a widespread use since the popularity of high-resolution 3D sensors.
no code implementations • ICCV 2015 • David Varas, Mónica Alfaro, Ferran Marques
This paper presents a co-clustering technique that, given a collection of images and their hierarchies, clusters nodes from these hierarchies to obtain a coherent multiresolution representation of the image collection.
no code implementations • CVPR 2014 • David Varas, Ferran Marques
We present a video object segmentation approach that extends the particle filter to a region-based image representation.