The deep learning technique has proven to be effective in the classification and localization
of objects on the image or ground plane over time. The strength of the technique's features …

Video-based human activity recognition (HAR) is an important task in many fields, such as
healthcare monitoring, video surveillance, and sports analysis. This review paper aims to …

The state of the art in video understanding suffers from two problems:(1) The major part of
reasoning is performed locally in the video, thus missing important relationships within …

Temporal action localization is an important yet challenging problem. Given a long,
untrimmed video consisting of multiple action instances and complex background contents …

Human activity recognition (HAR) is a complex and multifaceted problem. The research
community has reported numerous approaches to perform HAR. Along with HAR …

We address the problem of online action segmentation for egocentric procedural task
videos. While previous studies have mostly focused on offline action segmentation where …

Automatically recognizing and localizing wide ranges of human actions are crucial for video
understanding. Towards this goal, the THUMOS challenge was introduced in 2013 to serve …

General human action recognition requires understanding of various visual cues. In this
paper, we propose a network architecture that computes and integrates the most important …

Humans drive in a holistic fashion which entails, in particular, understanding dynamic road
events and their evolution. Injecting these capabilities in autonomous vehicles can thus take …

In contrast to the widely studied problem of recognizing an action given a complete
sequence, action anticipation aims to identify the action from only partially available videos …