Ponències/Comunicacions de congressos
Recent Submissions
-
VLX-Stories: building an online Event Knowledge Base with Emerging Entity detection
(Springer, 2019)
Conference lecture
Restricted access - publisher's policyWe present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by ... -
Budget-aware semi-supervised semantic and instance segmentation
(2019)
Conference lecture
Open AccessMethods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms ... -
Residual attention graph convolutional network for geometric 3D scene classification
(Institute of Electrical and Electronics Engineers (IEEE), 2019)
Conference report
Restricted access - publisher's policyGeometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible ... -
VLX-Stories: a semantically linked event platform for media publishers
(CEUR-WS.org, 2019)
Conference lecture
Open AccessIn the recent years, video sharing in social media from different video recording devices has resulted in a exponential growth of videos on the Internet. Such video data is continuously increasing with daily recordings ... -
Hyperparameter-free losses for model-based monocular reconstruction
(Institute of Electrical and Electronics Engineers (IEEE), 2019)
Conference lecture
Open AccessThis work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM). We dispense with the hyperparameters used in other works by exploiting geometry, so that the shape of the ... -
Picking groups instead of samples: a close look at Static Pool-based Meta-Active Learning
(Institute of Electrical and Electronics Engineers (IEEE), 2019)
Conference lecture
Open AccessActive Learning techniques are used to tackle learning problems where obtaining training labels is costly. In this work we use Meta-Active Learning to learn to select a subset of samples from a pool of unsupervised input ... -
Simple vs complex temporal recurrences for video saliency prediction
(2019)
Conference lecture
Restricted access - publisher's policyThis paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the ... -
Video object linguistic grounding
(Association for Computing Machinery (ACM), 2019)
Conference lecture
Restricted access - publisher's policyThe goal of this work is segmenting on a video sequence the objects which are mentioned in a linguistic description of the scene. We have adapted an existing deep neural network that achieves state of the art performance ... -
Multi-view 3D face reconstruction in the wild using siamese networks
(Computer Vision Foundation, 2019)
Conference report
Open AccessIn this work, we present a novel learning based approach to reconstruct 3D faces from a single or multiple images. Our method uses a simple yet powerful architecture based on siamese neural networks that helps to extract ... -
Digitally stained confocal microscopy through deep learning
(Microtome Publishing, 2019)
Conference report
Open AccessSpecialists have used confocal microscopy in the ex-vivo modality to identify Basal Cell Carcinoma tumors with an overall sensitivity of 96.6% and specificity of 89.2% (Chung et al., 2004). However, this technology hasn’t ... -
Wav2Pix: speech-conditioned face generation using generative adversarial networks
(Institute of Electrical and Electronics Engineers (IEEE), 2019)
Conference lecture
Restricted access - publisher's policySpeech 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 images of a speaker by conditioning a ... -
RVOS: end-to-end recurrent network for video object segmentation
(Computer Vision Foundation, 2019)
Conference lecture
Open AccessMultiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. ...
RSS 1.0