SPS Webinars

Radial sampling pattern is an important signal acquisition strategy in magnetic resonance imaging (MRI) owing to better immunity to motion-induced artifacts and less pronounced aliasing due to undersampling compared to the Cartesian sampling. 

Decentralized stochastic gradient descent (SGD) is a driving engine for decentralized federated learning (DFL). The performance of decentralized SGD is jointly influenced by inter-node communications and local updates.

Human centric visual analysis tasks are essential to computer vision since humans are the key element for cameras to analyze. In this talk, I will mainly focus on 4 visual analysis tasks on human hand, gesture, pose, and action respectively.

Graph neural networks (GNNs) have achieved impressive results in various graph learning tasks and they have found their way into many application domains. Despite their proliferation, our understanding of their robustness properties is still very limited. 

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this work explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. 

Recent advances in multimodal processing have led to promising solutions for speech-processing tasks. One example is automatic speech recognition (ASR), which is a key component in current speech-based systems.

Brain data are inherently large scale, multidimensional, and noisy. Indeed, advances in imaging and sensor technology allow recordings of ever-increasing spatio-temporal resolution. Multidimensional, as time series data are recorded at multiple locations (electrodes, voxels), from multiple subjects, under various conditions.

In the cognitive neurosciences and machine learning, we have formal ways of understanding and characterising perception and decision-making; however, the approaches appear very different: current formulations of perceptual synthesis call on theories like predictive coding and Bayesian brain hypothesis. 

While message-passing neural networks (MPNNs) are the most popular architectures for graph learning, their expressive power is inherently limited. In order to gain increased expressive power while retaining efficiency, several recent works apply MPNNs to subgraphs of the original graph.