(Vision Paper) A Vision for Spatio-Causal Situation Awareness, Forecasting, and Planning

FT Azad, KS Candan, A Kapkiç, ML Li, H Liu… - ACM Transactions on …, 2024 - dl.acm.org
Successfully tackling many urgent challenges in socio-economically critical domains, such
as public health and sustainability, requires a deeper understanding of causal relationships …

Cross-Layer Contrastive Learning of Latent Semantics for Facial Expression Recognition

W **e, Z Peng, L Shen, W Lu, Y Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have achieved significant improvement for the task of
facial expression recognition. However, current training still suffers from the inconsistent …

A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

W Wei, L Zhang, K Yang, J Li, N Cui, Y Han, N Zhang… - Heliyon, 2024 - cell.com
Traffic sign recognition is an important part of intelligent transportation system. It uses
computer vision and traffic sign recognition technology to detect and recognize traffic signs …

Sdma: Saliency-driven mutual cross attention for multi-variate time series

Y Garg, KS Candan - 2020 25th International Conference on …, 2021 - ieeexplore.ieee.org
The integration of rich sensory technologies into critical applications, such as gesture
recognition and building energy optimization, has highlighted the importance of intelligent …

iSparse: Output informed sparsification of neural network

Y Garg, KS Candan - Proceedings of the 2020 international conference …, 2020 - dl.acm.org
Deep neural networks have demonstrated unprecedented success in various multimedia
applications. However, the networks created are often very complex, with large numbers of …

Xm2a: Multi-scale multi-head attention with cross-talk for multi-variate time series analysis

Y Garg, KS Candan - 2021 IEEE 4th International Conference …, 2021 - ieeexplore.ieee.org
Advances in sensory technologies are enabling the capture of a diverse spectrum of real-
world data streams. In-creasing availability of such data, especially in the form of multi …

Deep Learning Segmentation Based Attention Mechanism Module for Navigation System

M Mawblei, J Binong - 2023 4th International Conference on …, 2023 - ieeexplore.ieee.org
This study implements state-of-the-art segmentation models on the unique conflate Area-of-
Focus dataset. The goal is to accurately identify and segment a specific regions in images …

On Feature Saliency and Deep Neural Networks

Y Garg - 2020 - keep.lib.asu.edu
Technological advances have allowed for the assimilation of a variety of data, driving a shift
away from the use of simpler and constrained patterns to more complex and diverse patterns …