Related papers: ALERT-Transformer: Bridging Asynchronous and Synch…

Event cameras record sparse illumination changes with high temporal resolution and high dynamic range. Thanks to their sparse recording and low consumption, they are increasingly used in applications such as AR/VR and autonomous driving.…

While model architectures and training strategies have become more generic and flexible with respect to different data modalities over the past years, a persistent limitation lies in the assumption of fixed quantities and arrangements of…

Bio-inspired Address Event Representation (AER) sensors have attracted significant popularity owing to their low power consumption, high sparsity, and high temporal resolution. Spiking Neural Network (SNN) has become the inherent choice for…

Performance optimization is an increasingly challenging but often repetitive task. While each platform has its quirks, the underlying code transformations rely on data movement and computational characteristics that recur across…

We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM)…

Human Activity Recognition (HAR) using wearable sensor data has become a central task in mobile computing, healthcare, and human-computer interaction. Despite the success of traditional deep learning models such as CNNs and RNNs, they often…

Event cameras are ideally suited to capture High Dynamic Range (HDR) visual information without blur but provide poor imaging capability for static or slowly varying scenes. Conversely, conventional image sensors measure absolute intensity…

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization…

In this work, we present a generalized formulation of the Transformer algorithm by reinterpreting its core mechanisms within the framework of Path Integral formalism. In this perspective, the attention mechanism is recast as a process that…

Sensor-based human activity recognition is a key technology for many human-centered intelligent applications. However, this research is still in its infancy and faces many unresolved challenges. To address these, we propose a comprehensive…

Emergent learning transforms a disordered optical medium into a photonic device capable of storage, recognition, and classification of arbitrary memory patterns. First, we show that the intensity at the output of a multiply scattering…

Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks…

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied. More especially, the event timestamps can carry important information about the underlying network dynamics,…

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieves state-of-the art…

Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies. This paper presents a novel transformer architecture for time series forecasting,…

Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems. Recent studies suggest that diffusion…