334 citations · 652 across the 18 of their papers we have counts for
19 papers
Sign Language Translation from Instructional Videos
Laia Tarrés, Gerard I. Gállego, Amanda Duarte +2
The advances in automatic sign language translation (SLT) to spoken languages have been mostly benchmarked with datasets of limited size and restricted domains. Our work advances t…
Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22
Laia Tarrés, Gerard I. Gàllego, Xavier Giró-i-Nieto +1
This paper describes the system developed at the Universitat Politècnica de Catalunya for the Workshop on Machine Translation 2022 Sign Language Translation Task, in particular, fo…
Topic Detection in Continuous Sign Language Videos
Alvaro Budria, Laia Tarres, Gerard I. Gallego +3
Significant progress has been made recently on challenging tasks in automatic sign language understanding, such as sign language recognition, translation and production. However, t…
Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation
Josep Lluis Berral, Oriol Aranda, Juan Luis Dominguez +1
Most research on novel techniques for 3D Medical Image Segmentation (MIS) is currently done using Deep Learning with GPU accelerators. The principal challenge of such technique is…
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation
Miriam Bellver, Carles Ventura, Carina Silberer +3
The task of video object segmentation with referring expressions (language-guided VOS) is to, given a linguistic phrase and a video, generate binary masks for the object to which t…
Mask-guided sample selection for Semi-Supervised Instance Segmentation
Miriam Bellver, Amaia Salvador, Jordi Torres +1
Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint…
How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language
Amanda Duarte, Shruti Palaskar, Lucas Ventura +5
One of the factors that have hindered progress in the areas of sign language recognition, translation, and production is the absence of large annotated datasets. Towards this end,…
Improving accuracy and speeding up Document Image Classification through parallel systems
Javier Ferrando, Juan Luis Dominguez, Jordi Torres +5
This paper presents a study showing the benefits of the EfficientNet models compared with heavier Convolutional Neural Networks (CNNs) in the Document Classification task, essentia…
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
Víctor Campos, Alexander Trott, Caiming Xiong +3
Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empow…
Budget-aware Semi-Supervised Semantic and Instance Segmentation
Miriam Bellver, Amaia Salvador, Jordi Torres +1
Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitig…
Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
Amanda Duarte, Francisco Roldan, Miquel Tubau +7
Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face i…
Importance Weighted Evolution Strategies
Víctor Campos, Xavier Giro-i-Nieto, Jordi Torres
Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds…
Cross-modal Embeddings for Video and Audio Retrieval
Didac Surís, Amanda Duarte, Amaia Salvador +2
The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube…
Recurrent Neural Networks for Semantic Instance Segmentation
Amaia Salvador, Miriam Bellver, Victor Campos +4
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our…
Detection-aided liver lesion segmentation using deep learning
Miriam Bellver, Kevis-Kokitsi Maninis, Jordi Pont-Tuset +3
A fully automatic technique for segmenting the liver and localizing its unhealthy tissues is a convenient tool in order to diagnose hepatic diseases and assess the response to the…
Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Victor Campos, Brendan Jou, Xavier Giro-i-Nieto +2
Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow infer…
Disentangling Motion, Foreground and Background Features in Videos
Xunyu Lin, Victor Campos, Xavier Giro-i-Nieto +2
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on moti…
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
Junting Pan, Cristian Canton Ferrer, Kevin McGuinness +4
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator mo…
Hierarchical Object Detection with Deep Reinforcement Learning
Miriam Bellver, Xavier Giro-i-Nieto, Ferran Marques +1
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that…