Related papers: BiHDTrans: binary hyperdimensional transformer for…
Transformers have become keystone models in natural language processing over the past decade. They have achieved great popularity in deep learning applications, but the increasing sizes of the parameter spaces required by transformer models…
Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…
The so-called block-term decomposition (BTD) tensor model has been recently receiving increasing attention due to its enhanced ability of representing systems and signals that are composed of \emph{blocks} of rank higher than one, a…
Achieving high-precision light manipulation is crucial for delivering information through complex media with high fidelity. However, existing spatial light modulation devices face a fundamental tradeoff between speed and accuracy. Digital…
Hyperdimensional computing (HDC) is an emerging computational framework that takes inspiration from attributes of neuronal circuits such as hyperdimensionality, fully distributed holographic representation, and (pseudo)randomness. When…
This study proposes a novel perspective on multimodal deep learning for biomedical signal classification, systematically analyzing how complementary feature domains impact model performance. While fusing multiple domains often presumes…
We present a novel bi-directional Transformer architecture (BiXT) which scales linearly with input size in terms of computational cost and memory consumption, but does not suffer the drop in performance or limitation to only one input…
High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge…
Human digital twins (HDTs) are dynamic, data-driven virtual representations of individuals, continuously updated with multimodal data to simulate, monitor, and predict health trajectories. By integrating clinical, physiological, behavioral,…
Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies like binarization are studied to…
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However,…
Brain-inspired Hyperdimensional (HD) computing is an emerging technique for cognitive tasks in the field of low-power design. As a fast-learning and energy-efficient computational paradigm, HD computing has shown great success in many…
3D Swin Transformer (3D-ST) known for its hierarchical attention and window-based processing, excels in capturing intricate spatial relationships within images. Spatial-spectral Transformer (SST), meanwhile, specializes in modeling…
Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis. Dense GPS methods preserve fine-grained evidence such as abnormal speeds and short-duration events, but their quadratic cost makes…
Alcohol consumption has a significant impact on individuals' health, with even more pronounced consequences when consumption becomes excessive. One approach to promoting healthier drinking habits is implementing just-in-time interventions,…
The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware.…
Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively…
In the era of the Internet of Things (IoT), where smartphones, built-in systems, wireless sensors, and nearly every smart device connect through local networks or the internet, billions of smart things communicate with each other and…
Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection…
This paper explores the novel deep learning Transformers architectures for high-frequency Bitcoin-USDT log-return forecasting and compares them to the traditional Long Short-Term Memory models. A hybrid Transformer model, called…