Probabilistic Graph Attention Network With Conditional Kernels for Pixel-Wise…

Multi-scale representations deeply learned via convolutional neural networks have shown tremendous importance for various pixel-level prediction problems. In this paper we present a novel approach …

Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers

In this article, we address the problem of tracking multiple speakers via the fusion of visual and auditory information. We propose to exploit the complementary nature and roles of these two modali…

A Comprehensive Analysis of Deep Regression

Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks. Vision tasks, such as human pose estimation, did…

Em Algorithms for Weighted-Data Clustering Application to Audio-Visual Scene …

SALSA: A Novel Dataset for Multimodal Group Behavior Analysis