Deep learning has made substantial breakthroughs in many fields due to its powerful
automatic representation capabilities. It has been proven that neural architecture design is …

Video action recognition is widely applied in video indexing, intelligent surveillance,
multimedia understanding, and other fields. Recently, it was greatly improved by …

The research progress in multimodal learning has grown rapidly over the last decade in
several areas, especially in computer vision. The growing potential of multimodal data …

Temporal action proposal generation is an challenging and promising task which aims to
locate temporal regions in real-world videos where action or event may occur. Current …

This work focuses on the task of elderly activity recognition, which is a challenging task due
to the existence of individual actions and human-object interactions in elderly activities …

Understanding videos is one of the fundamental directions in computer vision research, with
extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and …

The purpose of this study is to determine whether current video datasets have sufficient data
for training very deep convolutional neural networks (CNNs) with spatio-temporal three …

Learning to capture long-range relations is fundamental to image/video recognition. Existing
CNN models generally rely on increasing depth to model such relations which is highly …

Despite the steady progress in video analysis led by the adoption of convolutional neural
networks (CNNs), the relative improvement has been less drastic as that in 2D static image …

Temporal action proposal generation is an important yet challenging problem, since
temporal proposals with rich action content are indispensable for analysing real-world …