Search Results

Recently, several trackers utilising Transformer architecture have shown significant performance improvement. However, the high computational cost of multi‐head attention, a core component in the Transformer, has limited real‐time running speed,...

The authors propose a novel adaptive attention for tracking task that enhances features through spatial sparse attention mechanism with less than 1/4 of the computational complexity of multi‐head attention. Based on adaptive attention, the authors build ...

In this paper, we develop a progressive local and non-local interactive network with multi-scale cross-content deeply discriminative learning to solve image deraining. The proposed model contains two key techniques: 1) Progressive Local and Non-Local ...

This paper extends prior work on sparse tensor algebra compilers to generate asymptotically efficient code for tensor expressions with affine subscript expressions. Our technique enables compiler support for a wide range of sparse computations, including ...

Given the computational complexity of deep neural networks (DNN), accurate prediction of their training and inference time using performance modeling is crucial for efficient infrastructure planning and DNN development. However, existing methods often ...

Predicting the properties of molecular crystals is imperative to the field of materials design. In lieu of alternative methods, advances in machine learning have made it possible to predict the properties of materials before synthesis. This is ...

Human action recognition based on graph convolutional networks (GCNs) is one of the hotspots in computer vision. However, previous methods generally rely on handcrafted graph, which limits the effectiveness of the model in characterising the ...

The authors propose a multi‐scale skeleton simplification graph convolutional network (M3S‐GCN) for skeleton‐based action recognition. The model leverages skeleton simplification and multi‐scale modelling to effectively capture the intricate connections ...

The desire to empower resource-limited edge devices with computer vision (CV) must overcome the high energy consumption of collecting and processing vast sensory data. To address the challenge, this work proposes an energy-efficient non-von-Neumann in-...

Efficient image processing is increasingly crucial in constrained embedded and real-time platforms, especially in emerging applications such as Autonomous Driving (AD) or Augmented/Virtual Reality (AR/VR). A commonality among most image processing ...

Skeleton‐based action recognition has received much attention and achieved remarkable achievements in the field of human action recognition. In time series action prediction for different scales, existing methods mainly focus on attention ...

The authors introduce a novel Temporal Channel Reconfiguration Multi‐Graph Convolution Network (TRMGCN) that addresses limitations in existing methods for skeleton‐based action recognition by introducing the Temporal Channel Fusion with Guidance (TCFG) ...

Traffic noise pollution is a significant source of urban pollution. Roadside noise barriers (RNBs) serve as a primary solution to urban traffic noise pollution, but achieving precise positioning of RNBs requires on-site inspections and manual labeling, ...

Machine Learning (ML) models execute several parallel computations including Generalized Matrix Multiplication, Convolution, Dropout, etc. These computations are commonly executed on Graphics Processing Units (GPUs), by dividing the computation into ...

Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like ...

Extracting more information from feature interactions is essential to improve click-through rate (CTR) prediction accuracy. Although deep learning technology can help capture high-order feature interactions, the combination of features lacks ...

The utilisation of advanced algorithms in detecting blue sheep populations offers significant real-time statistical data for blue sheep protection. However, numerous classical algorithms employ convolution structures as fundamental units for data ...

Anomaly detection is a crucial step in any diagnostic procedure. With the advent of continuous monitoring devices, it is inevitable to use technological assistance for the same. Many methods, including autoencoders, have been proposed for anomaly ...

Neural fields are evolving towards a general-purpose continuous representation for visual computing. Yet, despite their numerous appealing properties, they are hardly amenable to signal processing. As a remedy, we present a method to perform general ...

Convolution kernels are widely seen in deep learning workloads and are often responsible for performance bottlenecks. Recent research has demonstrated that a direct convolution approach can outperform the traditional convolution implementation based on ...

Grasping detection, which involves identifying and assessing the grasp ability of objects by robotic systems, has garnered significant attention in recent years due to its pivotal role in the development of robotic systems and automated assembly ...

In order to solve the problem of low detection accuracy in robot grasping detection, a new model is proposed in this paper, which uses the attention module to extract RGB and depth channels. Then, the feature fusion module is used to combine these ...

Image Compressive Sensing (CS) enables compressed capture of natural images via a spatial multiplexing camera and accurate reconstruction from few measurements via an advanced algorithm. Deep learning, especially deep unfolding, has recently achieved ...

With the rising need for efficient image processing in emerging applications such as Autonomous Driving (AD) and Augmented/Virtual Reality (AR/VR), many existing solutions do not meet their performance and energy efficiency requirements or are domain-...