2k citations
- Joost van de Weijer3 profiles14 · h 66
- Sergio Escalera13 · h 73
- Dimosthenis Karatzas2 profiles9 · h 40
- P. Radeva8 · h 46
- Antonio M. López6 · h 39
- Ernest Valveny6 · h 31
- Mariella Dimiccoli6 · h 19
- Isabelle M Guyon5 · h 71
- Xavier Baró5 · h 31
- Abel Gonzalez-Garcia4 · h 17
- David Vázquez2 profiles4 · h 20
- F. Khan4 · h 96
- Universitat Autònoma de BarcelonaES58 papers
- Universitat de BarcelonaES26 papers
- Barcelona Supercomputing CenterES9 papers
- Centre de Recerca MatemàticaES4 papers
- Chinese Academy of SciencesCN4 papers
- Linköping UniversitySE4 papers
- Universitat Politècnica de CatalunyaES4 papers
- Mila - Quebec Artificial Intelligence InstituteCA3 papers
- Universitat Oberta de CatalunyaES3 papers
- Universitat Pompeu FabraES3 papers
- Université Paris-SaclayFR3 papers
- University of Chinese Academy of SciencesCN3 papers
6 papers · 2 filters
EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA
Arka Ujjal Dey, Ernest Valveny, Gaurav Harit
The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-…
Saliency for free: Saliency prediction as a side-effect of object recognition
Carola Figueroa-Flores, David Berga, Joost van der Weijer +1
Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth salien…
ChaLearn Looking at People: Inpainting and Denoising challenges
Sergio Escalera, Marti Soler, Stephane Ayache +6
Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence. However, in the context of computer vision, the pro…
Deep unsupervised 3D human body reconstruction from a sparse set of landmarks
Meysam Madadi, Hugo Bertiche, Sergio Escalera
In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a d…
On Implicit Attribute Localization for Generalized Zero-Shot Learning
Shiqi Yang, Kai Wang, Luis Herranz +1
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often…
Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz
We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-no…