Related papers: A Transformer-based deep neural network model for …

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are…

Deep learning models achieve strong performance across various domains but often rely on spurious correlations, making them vulnerable to distribution shifts. This issue is particularly severe in subpopulation shift scenarios, where models…

In the past, optimization-based registration models have used spatially-varying regularization to account for deformation variations in different image regions. However, deep learning-based registration models have mostly relied on…

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile…

The Deep Operator Network (DeepONet) structure has shown great potential in approximating complex solution operators with low generalization errors. Recently, a sequential DeepONet (S-DeepONet) was proposed to use sequential learning models…

Spiking neural networks (SNNs) have made great progress on both performance and efficiency over the last few years,but their unique working pattern makes it hard to train a high-performance low-latency SNN.Thus the development of SNNs still…

Rapid global urbanization is a double-edged sword, heralding promises of economical prosperity and public health while also posing unique environmental and humanitarian challenges. Smart and connected communities (S&CCs) apply data-centric…

Brain-Computer Interfaces (BCIs) implement a direct communication pathway between the brain of an user and an external device, as a computer or a machine in general. One of the most used brain responses to implement non-invasive BCIs is the…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

The key to electroencephalography (EEG)-based brain-computer interface (BCI) lies in neural decoding, and its accuracy can be improved by using hybrid BCI paradigms, that is, fusing multiple paradigms. However, hybrid BCIs usually require…

In this study, we introduce an innovative EEG signal reconstruction sub-module designed to enhance the performance of deep learning models on EEG eye-tracking tasks. This sub-module can integrate with all Encoder-Classifier-based deep…

Different categories of visual stimuli activate different responses in the human brain. These signals can be captured with EEG for utilization in applications such as Brain-Computer Interface (BCI). However, accurate classification of…

As various databases of facial expressions have been made accessible over the last few decades, the Facial Expression Recognition (FER) task has gotten a lot of interest. The multiple sources of the available databases raised several…

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

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…

The recent success of Transformer has provided a new direction to various visual understanding tasks, including video-based facial expression recognition (FER). By modeling visual relations effectively, Transformer has shown its power for…

Modern deep learning systems are typically deployed as open-loop function approximators: they map inputs to outputs in a single pass, without regulating how much computation or explanatory effort is spent on a given case. In safety-critical…

Saliency prediction has been extensively studied in RGB images and videos as a computational model of human visual attention. In contrast, predicting saliency from event-based data remains largely unexplored, despite the biological…

Sound event localization aims at estimating the positions of sound sources in the environment with respect to an acoustic receiver (e.g. a microphone array). Recent advances in this domain most prominently focused on utilizing deep…