Ponències/Comunicacions de congressos
Recent Submissions
-
Channel-wise early stopping without a validation set via NNK polytope interpolation
(2021)
Conference report
Open AccessState-of-the-art neural network architectures continue to scale in size and deliver impressive generalization results, although this comes at the expense of limited interpretability. In particular, a key challenge is to ... -
H3D-Net: Few-shot high-fidelity 3D head reconstruction
(Computer Vision Foundation, 2021)
Conference lecture
Open AccessRecent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D reconstruction. The effectiveness of these ... -
Seasonal contrast: Unsupervised pre-training from uncurated remote sensing data
(Computer Vision Foundation, 2021)
Conference lecture
Open AccessRemote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use monitoring, or tackling climate change. Although there exist vast amounts of remote sensing data, ... -
How2Sign: A large-scale multimodal dataset for continuous American sign language
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference lecture
Open AccessOne 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, we introduce How2Sign, a multimodal and ... -
Refinement network for unsupervised on the scene foreground segmentation
(European Association for Signal Processing (EURASIP), 2020)
Conference report
Open AccessUnsupervised learning represents one of the most interesting challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large ... -
Explore, discover and learn: unsupervised discovery of state-covering skills
(2020)
Conference lecture
Open AccessAcquiring 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 empowerment, which draws a connection between ... -
Weakly supervised semantic segmentation for remote sensing hyperspectral imaging
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference lecture
Restricted access - publisher's policyThis paper studies the problem of training a semantic segmentation neural network with weak annotations, in order to be applied in aerial vegetation images from Teide National Park. It proposes a Deep Seeded Region Growing ... -
One perceptron to rule them all: language, vision, audio and speech
(Association for Computing Machinery (ACM), 2020)
Conference lecture
Restricted access - publisher's policyDeep neural networks have boosted the convergence of multimedia data analytics in a unified framework shared by practitioners in natural language, vision and speech. Image captioning, lip reading or video sonorization are ... -
Automatic reminiscence therapy for dementia
(Association for Computing Machinery (ACM), 2020)
Conference lecture
Restricted access - publisher's policyWith people living longer than ever, the number of cases with dementia such as Alzheimer's disease increases steadily. It affects more than 46 million people worldwide, and it is estimated that in 2050 more than 100 million ... -
Audience measurement using a top-view camera and oriented trajectories
(2019)
Conference report
Restricted access - publisher's policyA crucial aspect for selecting optimal areas for commercial advertising is the probability with which that publicity will be seen. This paper presents a method based on top-view camera measurement, where the probability ... -
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 ...