-
ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction
Prediction of the action outcome is a new challenge for a robot collabor...
read it
-
Human Action Forecasting by Learning Task Grammars
For effective human-robot interaction, it is important that a robotic as...
read it
-
Human Action Recognition and Assessment via Deep Neural Network Self-Organization
The robust recognition and assessment of human actions are crucial in hu...
read it
-
Low-light Environment Neural Surveillance
We design and implement an end-to-end system for real-time crime detecti...
read it
-
An Empirical Evaluation On Vibrotactile Feedback For Wristband System
With the rapid development of mobile computing, wearable wrist-worn is b...
read it
-
Attentional Pooling for Action Recognition
We introduce a simple yet surprisingly powerful model to incorporate att...
read it
-
Scene recognition based on DNN and game theory with its applications in human-robot interaction
Scene recognition model based on the DNN and game theory with its applic...
read it
Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction
Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task in interaction scenarios and propose an attention-oriented multi-level network framework to meet the need for real-time interaction. Specifically, a Pre-Attention network is employed to roughly focus on the interactor in the scene at low resolution firstly and then perform fine-grained pose estimation at high resolution. The other compact CNN receives the extracted skeleton sequence as input for action recognition, utilizing attention-like mechanisms to capture local spatial-temporal patterns and global semantic information effectively. To evaluate our approach, we construct a new action dataset specially for the recognition task in interaction scenarios. Experimental results on our dataset and high efficiency (112 fps at 640 x 480 RGBD) on the mobile computing platform (Nvidia Jetson AGX Xavier) demonstrate excellent applicability of our method on action recognition in real-time human-robot interaction.
READ FULL TEXT
Comments
There are no comments yet.