Social Multimedia Signals
A Signal Processing Approach to Social Network Phenomena
Page
%P
-
Chapter and Conference Paper
Optimal Sampling Frequency of SVPWM for Multilevel Converter
With the increasing application of space vector pulse width modulation (SVPWM) strategy in multilevel converters, the sampling frequency selection of SVPWM algorithm becomes a new problem. This paper proposes ...
-
Chapter and Conference Paper
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of t...
-
Chapter and Conference Paper
Robust Multi-object Tracking by Marginal Inference
Multi-object tracking in videos requires to solve a fundamental problem of one-to-one assignment between objects in adjacent frames. Most methods address the problem by first discarding impossible pairs whose ...
-
Article
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appeal...
-
Article
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained...
-
Reference Work Entry In depth
Monocular and Binocular People Tracking
-
Living Reference Work Entry In depth
Monocular and Binocular People Tracking
-
Chapter and Conference Paper
VoxelPose: Towards Multi-camera 3D Human Pose Estimation in Wild Environment
We present VoxelPose to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D p...
-
Chapter and Conference Paper
Global Distance-Distributions Separation for Unsupervised Person Re-identification
Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain data. Unsupervised person ReID...
-
Chapter and Conference Paper
AF2S: An Anchor-Free Two-Stage Tracker Based on a Strong SiamFC Baseline
Siamese network based trackers have become a mainstream in visual object tracking. Recently, several high-performance multi-stage trackers have been proposed and some of them adopt SiamRPN for the first-stage ...
-
Chapter and Conference Paper
Towards a Better Match in Siamese Network Based Visual Object Tracker
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limi...
-
Chapter and Conference Paper
The Sixth Visual Object Tracking VOT2018 Challenge Results
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers...
-
Chapter and Conference Paper
Online Dictionary Learning for Approximate Archetypal Analysis
Archetypal analysis is an unsupervised learning approach which represents data by convex combinations of a set of archetypes. The archetypes generally correspond to the extremal points in the dataset and are l...
-
Chapter and Conference Paper
Adding Attentiveness to the Neurons in Recurrent Neural Networks
Recurrent neural networks (RNNs) are capable of modeling the temporal dynamics of complex sequential information. However, the structures of existing RNN neurons mainly focus on controlling the contributions o...
-
Article
Open AccessTargeting to the non-genomic activity of retinoic acid receptor-gamma by acacetin in hepatocellular carcinoma
We recently demonstrated that retinoic acid receptor-γ (RARγ) is overexpressed and acts as a tumor promoter in hepatocellular carcinoma (HCC). The oncogenic activity of RARγ is mainly attributed to its physiol...
-
Article
Open AccessOptimal electromagnetic hybrid negative current compensation method for high-speed railway power supply system
To achieve economical compensation for the huge-capacity negative sequence currents generated by high-speed railway load, an electromagnetic hybrid compensation system (EHCS) and control strategy is proposed. ...
-
Chapter and Conference Paper
Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging...
-
Book
-
Chapter
Web 2.x
The digital revolution has changed every aspect of our daily life. Powered by smaller devices and faster computer networks, humanity is living in the age of digital transposition—where many traditionally physi...
-
Chapter
The World of Signals
In this chapter, we first discuss the definition of signal and its relationship to information and knowledge. We then present a number of operations that have been developed to process signals for various appl...
