Related papers: Temporal Point-Supervised Signal Reconstruction: A…

Camera traps have revolutionized the animal research of many species that were previously nearly impossible to observe due to their habitat or behavior. They are cameras generally fixed to a tree that take a short sequence of images when…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…

Time series analysis plays a vital role in various applications, for instance, healthcare, weather prediction, disaster forecast, etc. However, to obtain sufficient shapelets by a feature network is still challenging. To this end, we…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. To solve this problem, this paper proposes a…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the…

Trend filtering simplifies complex time series data by applying smoothness to filter out noise while emphasizing proximity to the original data. However, existing trend filtering methods fail to reflect abrupt changes in the trend due to…

Spiking Neural Networks (SNNs) are biologically-inspired deep neural networks that efficiently extract temporal information while offering promising gains in terms of energy efficiency and latency when deployed on neuromorphic devices. SNN…

This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end…

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new…

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

Speech Emotion Recognition (SER) is widely deployed in Human-Computer Interaction, yet the high computational cost of conventional models hinders their implementation on resource-constrained edge devices. Spiking Neural Networks (SNNs)…

Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS.…

Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used saliency maps in…

Time-Sensitive Distributed Systems (TSDS), such as applications using autonomous drones, achieve goals under possible environment interference (\eg, winds). Moreover, goals are often specified using explicit time constraints which must be…

Fault diagnosis plays a crucial role in maintaining the operational integrity of mechanical systems, preventing significant losses due to unexpected failures. As intelligent manufacturing and data-driven approaches evolve, Deep Learning…

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

The diversity of time series applications and scarcity of domain-specific data highlight the need for time-series models with strong few-shot learning capabilities. In this work, we propose a novel training scheme and a transformer-based…

Recurrent neural networks (RNNs) are state-of-the-art in several sequential learning tasks, but they often require considerable amounts of data to generalise well. For many time series forecasting (TSF) tasks, only a few dozens of…