Information fusion is frequently employed to integrate diverse inputs, including sensory data,
features, or decisions, in order to leverage the advantageous relationships among various …

Human action recognition remains an important yet challenging task. This work proposes a
novel action recognition system. It uses a novel multi-view region-adaptive multi-resolution …

Automatic recognition of human activity, although a challenging task, it is particularly useful
in case of defence security applications, content-based video analysis, city crime prevention …

Nowadays, the recognition of group activities is a significant problem, specially in video
surveillance. It is increasingly important to have vision architectures that automatically allow …

One action of a human is completed under the control of the relevant system of body. The
realization of movements is complex, diverse, and detailed, with flexibility and variability that …

The traditional classification methods of PolSAR image generally required the feature
extraction in the early stage, involving more human participation, and the classification …

MobiSamadhaan is an artificial intelligence (AI)-based approach toward a universal mobility
solution for the problems concerning with daily hassles of traffic and unbalanced …

Automatic image captioning has been studied extensively over the last few years, driven by
breakthroughs in deep learning-based image-to-text translation models. However, most of …

Trajectories and spatiotemporal attention model have been successfully used in skeleton-
based action recognition. Most existing methods focus more attention on temporal structure …

PolSAR (Polarimetric Synthetic Aperture Radar) 图像分类的传统方法在前期需要对数据进行
特征提取, 涉及较多的人为参与, 且分类精度有待进a 步提高, 此外, 在采用监督分类方法时 …