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

We present a track-finding algorithm for the Belle II experiment that specifically targets so-called kinks: signatures of charged particles decaying or scattering in-flight in the detector material, resulting in a sudden and significant…

To handle the complexities of real-world traffic, learning planners for self-driving from data is a promising direction. While recent approaches have shown great progress, they typically assume a setting in which the ground-truth world…

We present a Siamese-like Dual-branch network based on solely Transformers for tracking. Given a template and a search image, we divide them into non-overlapping patches and extract a feature vector for each patch based on its matching…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Compared with previous two-stream trackers, the recent one-stream tracking pipeline, which allows earlier interaction between the template and search region, has achieved a remarkable performance gain. However, existing one-stream trackers…

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

This paper introduces a novel deep learning approach to predict the engineering properties of the ground improved by Rapid Impact Compaction (RIC), which is a ground improvement technique that uses a drop hammer to compact the soil and fill…

Some group activities, such as team sports and choreographed dances, involve closely coupled interaction between participants. Here we investigate the tasks of inferring and predicting participant behavior, in terms of motion paths and…

Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous…

Accurate and efficient estimation of Channel State Information (CSI) is critical for next-generation wireless systems operating under non-stationary conditions, where user mobility, Doppler spread, and multipath dynamics rapidly alter…

Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural language understanding (NLU) research. In this paper, we introduce…

The expected performance of track reconstruction with LHC events using the CMS silicon tracker is presented. Track finding and fitting is accomplished with Kalman Filter techniques that achieve efficiencies above 99% on single muons with…

We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality. We introduce an end-to-end network that performs early…

As experiments in high energy physics aims to measure increasingly rare processes, the experiments continually strive to increase the expected signal yields. In the case of the High Luminosity upgrade of the LHC, the luminosity is raised by…

We present an improved technique for estimating a muon's energy by measuring the deflections along its path inside the MicroBooNE detector from multiple Coulomb scattering (MCS). This approach implements several innovations that better…

In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems. Our approach innovatively confronts token explosion and…

While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer…

We present measurements of position and angular resolution of drift chambers operated with a Xe,CO$_2$(15%) mixture. The results are compared to Monte Carlo simulations and important systematic effects, in particular the dispersive nature…

This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of…

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…