Related papers: A hybrid deep learning approach to vertexing

In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we developed a deep learning method that is able to encode the latent space of indoor…

Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature grid representations often suffer from substantial memory…

The High Luminosity upgrade of the Large Hadron Collider (HL-LHC) will produce particle collisions with up to 200 simultaneous proton-proton interactions. These unprecedented conditions will create a combinatorial complexity for…

Deep Convolutional Neural Networks (CNNs) achieve high accuracy but often rely on purely global, gradient-based optimisation, which can lead to overfitting, redundant filters, and reduced interpretability. To address these limitations, we…

Knowledge hypergraph embedding models are usually computationally expensive due to the inherent complex semantic information. However, existing works mainly focus on improving the effectiveness of knowledge hypergraph embedding, making the…

Recent research in the field of Human Activity Recognition has shown that an improvement in prediction performance can be achieved by reducing the number of LSTM layers. However, this kind of enhancement is only significant on monolithic…

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual…

A large number of retinal vessel analysis methods based on image segmentation have emerged in recent years. However, existing methods depend on cumbersome backbones, such as VGG16 and ResNet-50, benefiting from their powerful feature…

Thanks to the tiny storage and efficient execution, hyperdimensional Computing (HDC) is emerging as a lightweight learning framework on resource-constrained hardware. Nonetheless, the existing HDC training relies on various heuristic…

We show how event topology classification based on deep learning could be used to improve the purity of data samples selected in real time at at the Large Hadron Collider. We consider different data representations, on which different kinds…

Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong…

Long-term point tracking is essential to understand non-rigid motion in the physical world better. Deep learning approaches have recently been incorporated into long-term point tracking, but most prior work predominantly functions in 2D.…

Reconstructing charged particle tracks is a fundamental task in modern collider experiments. The unprecedented particle multiplicities expected at the High-Luminosity Large Hadron Collider (HL-LHC) pose significant challenges for track…

Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from data scarcity and sparsity. Previous work has taken the first…

In recent times, the trend in very large scale integration (VLSI) industry is multi-dimensional, for example, reduction of energy consumption, occupancy of less space, precise result, less power dissipation, faster response. To meet these…

As data requirements continue to grow, efficient learning increasingly depends on the curation and distillation of high-value data rather than brute-force scaling of model sizes. In the case of a hyperspectral image (HSI), the challenge is…

The planned upgrade of the LHC accelerator at CERN, namely the high luminosity (HL) phase of the LHC (HL-LHC foreseen for 2023), will result in a more intense radiation environment than the present tracking system was designed for. The…

Recently, deep learning approach has achieved promising results in various fields of computer vision. In this paper, a new framework called Hierarchical Depth Motion Maps (HDMM) + 3 Channel Deep Convolutional Neural Networks (3ConvNets) is…

In the high luminosity scenario of the LHC (HL-LHC), which will bring the instantaneous luminosity up to 7.5\,$\times$\,$10^{34}$\,cm$^{-2}$s$^{-1}$, ATLAS and CMS will need to operate at up to 200 interactions per 25\,ns beam crossing and…