Related papers: KnowDis: Knowledge Enhanced Data Augmentation for …
Solving real-world problems, particularly with deep learning, relies on the availability of abundant, quality data. In this paper we develop a novel framework that maximises the utility of time-series datasets that contain only small…
Multimedia event detection has been receiving increasing attention in recent years. Besides recognizing an event, the discovery of evidences (which is refered to as "recounting") is also crucial for user to better understand the searching…
We introduce an approach which allows detecting causal relationships between variables for which the time evolution is available. Causality is assessed by a variational scheme based on the Information Imbalance of distance ranks, a…
Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others. This shortcut learning behaviour is detrimental to a network's ability to generalize to…
Understanding causality is a core aspect of intelligence. The Event Causality Identification with Causal News Corpus Shared Task addresses two aspects of this challenge: Subtask 1 aims at detecting causal relationships in texts, and Subtask…
Data augmentation is a key element of deep learning pipelines, as it informs the network during training about transformations of the input data that keep the label unchanged. Manually finding adequate augmentation methods and parameters…
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these…
A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very…
We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods rely on interactive expert labeling, additional…
Recent advances in deep learning (DL) have prompted the development of high-performing early warning score (EWS) systems, predicting clinical deteriorations such as acute kidney injury, acute myocardial infarction, or circulatory failure.…
Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end…
Event-based cameras provide accurate and high temporal resolution measurements for performing computer vision tasks in challenging scenarios, such as high-dynamic range environments and fast-motion maneuvers. Despite their advantages,…
Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated…
Change Detection (CD) is an essential field in remote sensing, with a primary focus on identifying areas of change in bi-temporal image pairs captured at varying intervals of the same region by a satellite. The data annotation process for…
Cross-domain recommendation forms a crucial component in recommendation systems. It leverages auxiliary information through source domain tasks or features to enhance target domain recommendations. However, incorporating inconsistent source…
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, we explore how expert knowledge can be used to improve the data-driven identification of causal graphs,…
The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations…
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…
Physiological and behavioral data collected from wearable or mobile sensors have been used to estimate self-reported stress levels. Since the stress annotation usually relies on self-reports during the study, a limited amount of labeled…