Ponències/Comunicacions de congressos
Recent Submissions
-
Using player's body-orientation to model pass feasibility in soccer
(2020)
Conference report
Open AccessGiven a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and ... -
The TALP-UPC participation in WMT21 news translation task: an mBART-based NMT approach
(Association for Computational Linguistics, 2021)
Conference report
Open AccessThis paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission ... -
Neural cellular automata manifold
(IEEE Computer Society Conference Publishing Services (CPS), 2021)
Conference report
Open AccessVery recently, the Neural Cellular Automata (NCA) has been proposed to simulate the morphogenesis process with deep networks. NCA learns to grow an image starting from a fixed single pixel. In this work, we show that the ... -
Choosing the root of the tree decomposition when solving WCSPs: preliminary results
(IOS Press, 2021)
Conference report
Open AccessIn this paper we analyze the effect of selecting the root in a tree decomposition when using decomposition-based backtracking algorithms. We focus on optimization tasks for Graphical Models using the BTD algorithm. We show ... -
Applying and verifying an explainability method based on policy graphs in the context of reinforcement learning
(IOS Press, 2021)
Conference report
Open AccessThe advancement on explainability techniques is quite relevant in the field of Reinforcement Learning (RL) and its applications can be beneficial for the development of intelligent agents that are understandable by humans ... -
Everything transformers: Recognition, classification and normalisation of professions and family relations
(CEUR-WS.org, 2021)
Conference report
Open AccessThis document describes the system submitted by TALP team for IberLEF 2021’s MEDDOPROF Shared Task. The joint occupation mention identification and family relation classification model is composed of a pre-trained DistilBERT ... -
Real-time multimodal emotion classification system in E-Learning context
(Springer, 2021)
Conference report
Restricted access - publisher's policyEmotions of learners are crucial and important in e-learning as they promote learning. To investigate the effects of emotions on improving and optimizing the outcomes of e-learning, machine learning models have been proposed ... -
TALP at eHealth-KD Challenge 2020: Multi-level recurrent and convolutional neural networks for joint classification of key-phrases and relations
(CEUR-WS.org, 2020)
Conference report
Open AccessThis article describes the model presented by the TALP Team to IberLEF’s eHealth Knowledge Discovery 2020 shared task[1]. The model iterates over the idea of using a single model for simultaneously identify key-phrases and ... -
Denoising wavefront sensor image with deep neural networks
(International Society for Photo-Optical Instrumentation Engineers (SPIE), 2020)
Conference report
Open AccessA classical closed-loop adaptive optics system with a Shack-Hartmann wavefront sensor (WFS) relies on a center of gravity approach to process the WFS information and an integrator with gain to produce the commands to a ... -
Textual visual semantic dataset for text spotting
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference report
Open AccessText Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging problem due to the complexity of the context ... -
Building graph representations of deep vector embeddings
(Association for Computational Linguistics, 2017)
Conference lecture
Open AccessPatterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector ... -
Full-network embedding in a multimodal embedding pipeline
(Association for Computational Linguistics, 2017)
Conference lecture
Open AccessThe current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this ...
RSS 1.0