Related papers: HierCVAE: Hierarchical Attention-Driven Conditiona…

Numerical weather forecasting using high-resolution physical models often requires extensive computational resources on supercomputers, which diminishes their wide usage in most real-life applications. As a remedy, applying deep learning…

Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models. There is a consensus that the top-down hierarchical VAEs allow effective learning of deep latent structures and avoid problems like…

The growing complexity and scale of scientific workflows in high performance computing (HPC) environments have led to significant challenges in managing energy consumption without compromising computational performance. Traditional…

The attention mechanism is blooming in computer vision nowadays. However, its application to video quality assessment (VQA) has not been reported. Evaluating the quality of in-the-wild videos is challenging due to the unknown of pristine…

Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets. Deep learning models like the DeepConvLSTM…

Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for…

Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent…

Adaptive controllers on quadrotors typically rely on estimation of disturbances to ensure robust trajectory tracking. Estimating disturbances across diverse environmental contexts is challenging due to the inherent variability and…

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

Variational Autoencoders (VAEs) have recently been highly successful at imputing and acquiring heterogeneous missing data. However, within this specific application domain, existing VAE methods are restricted by using only one layer of…

Assigning consistent temporal identifiers to multiple moving objects in a video sequence is a challenging problem. A solution to that problem would have immediate ramifications in multiple object tracking and segmentation problems. We…

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Due to potential applications in chronic disease management and personalized healthcare, the EHRs data analysis has attracted much attention of both researchers and practitioners. There are three main challenges in modeling longitudinal and…

Load modeling is difficult due to its uncertain and time-varying properties. Through the recently proposed ambient signals load modeling approach, these properties can be more frequently tracked. However, the large dataset of load modeling…

We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-attention. Self-attention requires the key-value (KV) cache of…

Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not…

This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual…

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it…

Long-term traffic prediction has always been a challenging task due to its dynamic temporal dependencies and complex spatial dependencies. In this paper, we propose a model that combines hybrid Transformer and spatio-temporal…

Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data…