Related papers: Transformer-Based Approach to Enhance Positron Tra…

Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and…

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…

High-Energy Physics experiments are facing a multi-fold data increase with every new iteration. This is certainly the case for the upcoming High-Luminosity LHC upgrade. Such increased data processing requirements forces revisions to almost…

The coherent conversion of a muon to an electron in a nuclear field has been one of the most powerful methods for searching for charged lepton flavor violation. Recent advancements have significantly enhanced the sensitivity of $\mu…

We describe and show results of a photographic technique for continuously monitoring the position, orientation, and shape of a thin-film muon stopping target for the MEG II experiment. The measurement is complicated by the target being…

The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and…

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

The widespread use of GPS devices has driven advances in spatiotemporal data mining, enabling machine learning models to simulate human decision making and generate realistic trajectories, addressing both data collection costs and privacy…

The performance of missing transverse momentum reconstruction algorithms is presented using 8 TeV pp collision data collected with the CMS detector, corresponding to an integrated luminosity of $12.2 \pm 0.5$ $\mathrm{fb^{-1}}$. The scale…

Accurate machine-learning models for aerodynamic prediction are essential for accelerating shape optimization, yet remain challenging to develop for complex three-dimensional configurations due to the high cost of generating training data.…

Tau leptons serve as an important tool for studying the production of Higgs and electroweak bosons, both within and beyond the Standard Model of particle physics. Accurate reconstruction and identification of hadronically decaying tau…

Gas detectors are one of the pillars of the research in fundamental physics. Since many years, a new concept of detectors, the Micro Pattern Gas Detectors, allows to overcome many of the problems of other types of commonly used detectors,…

Based on real data, a new parameterized model of the Main Drift Chamber response is proposed. In this model, we tune the ratio of good hits and the residual distribution separately. The difference between simulation and data in track…

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

Track reconstruction is a vital aspect of High-Energy Physics (HEP) and plays a critical role in major experiments. In this study, we delve into unexplored avenues for particle track reconstruction and hit clustering. Firstly, we enhance…

Particle track reconstruction is the most computationally intensive process in nuclear physics experiments. Traditional algorithms use a combinatorial approach that exhaustively tests track measurements ("hits") to identify those that form…

This paper presents an innovative Transformer-based deep learning strategy for optimizing the placement of sensors aiming at structural health monitoring of semiconductor probe cards. Failures in probe cards, including substrate cracks and…

Real-time human motion reconstruction from a sparse set of (e.g. six) wearable IMUs provides a non-intrusive and economic approach to motion capture. Without the ability to acquire position information directly from IMUs, recent works took…

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing…

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…