Results 61 to 70 of about 1,365,020 (307)

Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video [PDF]

IEEE/RJS International Conference on Intelligent RObots and Systems, 2019
Pushing is a fundamental robotic skill. Existing work has shown how to exploit models of pushing to achieve a variety of tasks, including grasping under uncertainty, in-hand manipulation and clearing clutter.
Maria Bauzá, Ferran Alet, Yen-Chen Lin, Tomas Lozano-Perez, L. Kaelbling, Phillip Isola, Alberto Rodriguez   +6 more
semanticscholar   +1 more source

Salient Object Detection in RGB-D Videos

IEEE Transactions on Image Processing
IEEE TIP (under major revision)
Ao Mou, Yukang Lu, Jiahao He, Dingyao Min, Keren Fu, Qijun Zhao   +5 more
openaire   +3 more sources

Spatiotemporal Relation Networks for Video Action Recognition

IEEE Access, 2019
Two-stream convolutional networks have shown strong performance in a video action recognition task for its ability to capture spatial and temporal features simultaneously.
Zheng Liu, Haifeng Hu
doaj   +1 more source

Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data

Italian National Conference on Sensors
Detecting violent behavior in videos to ensure public safety and security poses a significant challenge. Precisely identifying and categorizing instances of violence in real-life closed-circuit television, which vary across specifications and locations ...
Jae-Hyuk Park, Mohamed Mahmoud, H. Kang
semanticscholar   +1 more source

Depth-adaptive supervoxels for RGB-D video segmentation [PDF]

2013 IEEE International Conference on Image Processing, 2013
In this paper we present a method for automatic video segmentation of RGB-D video streams provided by combined colour and depth sensors like the Microsoft Kinect. To this end, we combine position and normal information from the depth sensor with colour information to compute temporally stable, depth-adaptive superpixels and combine them into a graph of
Weikersdorfer, D., Schick, Alexander, Cremers, D.   +2 more
openaire   +1 more source

Convolutional spatio-temporal sequential inference model for human interaction behavior recognition

Frontiers in Computer Science
IntroductionHuman action recognition is a critical task with broad applications and remains a challenging problem due to the complexity of modeling dynamic interactions between individuals.
Lizhong Jin, Rulong Fan, Xiaoling Han, Xueying Cui   +3 more
doaj   +1 more source

Shapeshifting Liquid Metal Droplets for Soft Fluidic Machines

Advanced Materials, EarlyView.
This study presented a liquid metal shape shifting strategy which harnesses Lorentz force, surface tension and fluid instabilities to achieve autonomous fluidic power. By using a liquid metal droplet as a mobile current carrier, this strategy enables the development of low‐voltage, self‐oscillating pumps that outperform existing soft pumps.
Saba Firouznia, Christian Romero, Hemma Philamore, Andrew Conn, Martin Garrad, Jonathan Rossiter   +5 more
wiley   +1 more source

Auxiliary Task Graph Convolution Network: A Skeleton-Based Action Recognition for Practical Use

Applied Sciences
Graph convolution networks (GCNs) have been extensively researched for action recognition by estimating human skeletons from video clips. However, their image sampling methods are not practical because they require video-length information for sampling ...
Junsu Cho, Seungwon Kim, Chi-Min Oh, Jeong-Min Park   +3 more
doaj   +1 more source

Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

Applied Sciences, 2019
Using video sequences to restore 3D human poses is of great significance in the field of motion capture. This paper proposes a novel approach to estimate 3D human action via end-to-end learning of deep convolutional neural network to calculate the ...
Xin Min, Shouqian Sun, Honglie Wang, Xurui Zhang, Chao Li, Xianfu Zhang   +5 more
doaj   +1 more source

Video Human Action Recognition Algorithm Based on Trained Image CNN Features [PDF]

Jisuanji gongcheng, 2017
In order to apply Convolutional Neural Network (CNN) to video understanding,a recognition algorithm based on trained image CNN features is proposed.Image RGB data is employed to recognize human action in videos.Off-the-shelf CNN models are used to ...
CAO Jinqi,JIANG Xinghao,SUN Tanfeng
doaj   +1 more source