A review of convolutional-neural-network-based action recognition
G Yao, T Lei, J Zhong - Pattern Recognition Letters, 2019 - Elsevier
Video action recognition is widely applied in video indexing, intelligent surveillance,
multimedia understanding, and other fields. Recently, it was greatly improved by …
multimedia understanding, and other fields. Recently, it was greatly improved by …
Going deeper into action recognition: A survey
Understanding human actions in visual data is tied to advances in complementary research
areas including object recognition, human dynamics, domain adaptation and semantic …
areas including object recognition, human dynamics, domain adaptation and semantic …
A comprehensive study of deep video action recognition
Video action recognition is one of the representative tasks for video understanding. Over the
last decade, we have witnessed great advancements in video action recognition thanks to …
last decade, we have witnessed great advancements in video action recognition thanks to …
Semantics for robotic mapping, perception and interaction: A survey
For robots to navigate and interact more richly with the world around them, they will likely
require a deeper understanding of the world in which they operate. In robotics and related …
require a deeper understanding of the world in which they operate. In robotics and related …
Self-supervised video representation learning with odd-one-out networks
We propose a new self-supervised CNN pre-training technique based on a novel auxiliary
task called odd-one-out learning. In this task, the machine is asked to identify the unrelated …
task called odd-one-out learning. In this task, the machine is asked to identify the unrelated …
Dynamic image networks for action recognition
We introduce the concept of dynamic image, a novel compact representation of videos
useful for video analysis especially when convolutional neural networks (CNNs) are used …
useful for video analysis especially when convolutional neural networks (CNNs) are used …
RGB-D-based human motion recognition with deep learning: A survey
Human motion recognition is one of the most important branches of human-centered
research activities. In recent years, motion recognition based on RGB-D data has attracted …
research activities. In recent years, motion recognition based on RGB-D data has attracted …
Toward human activity recognition: a survey
Human activity recognition (HAR) is a complex and multifaceted problem. The research
community has reported numerous approaches to perform HAR. Along with HAR …
community has reported numerous approaches to perform HAR. Along with HAR …
Rank pooling for action recognition
We propose a function-based temporal pooling method that captures the latent structure of
the video sequence data-eg, how frame-level features evolve over time in a video. We show …
the video sequence data-eg, how frame-level features evolve over time in a video. We show …
Action recognition with dynamic image networks
We introduce the concept of dynamic image, a novel compact representation of videos
useful for video analysis, particularly in combination with convolutional neural networks …
useful for video analysis, particularly in combination with convolutional neural networks …