Keyphrases
Active Speaker Detection
100%
Transnational Higher Education
66%
Pedestrian Detection
66%
Audio
56%
Feature Fusion
46%
Deep Learning Framework
44%
Feature Extracting
41%
Audio Features
40%
Facial Features
40%
Education Leader
33%
Education Manager
33%
Personal Well-being
33%
AUC Score
33%
Community Well-being
33%
Job Retention
33%
Higher Education Providers
33%
Development over Time
33%
Satisfying Experience
33%
Real-time Architecture
33%
Audio-visual Fusion
33%
Active Speaker
33%
Multi-scale Pedestrian Detection
33%
Personal Considerations
33%
Contour-aware
33%
Audiovisual Features
33%
Motivation Satisfaction
33%
Personal Interaction
33%
Cost Performance
33%
Job Satisfaction
33%
Inference Time
33%
Local Community
33%
Employee Experience
33%
Individual Perception
33%
Backers
33%
Project Category
33%
Kick
33%
Kickstarter
33%
Cost Savings
33%
Work-related
33%
Well-being
33%
Motivation
33%
Hybrid Channel
33%
Feature Pyramid Network
33%
ConvNet
33%
Feature Fusing
33%
Addressee Detection
33%
Social Capital
33%
Human-to-human
33%
Channel-based
33%
Time Application
33%
Computer Science
Feature Fusion
77%
Robot
66%
Deep Learning
66%
Learning Framework
66%
Detection Algorithm
66%
Extracted Feature
38%
Experimental Result
38%
Local Community
33%
Prediction Function
33%
Human Robot Interaction
33%
Skeletal Structure
33%
Fundamental Component
33%
Cost Saving
33%
Feature Extraction
33%
Real-Time Application
33%
Temporal Dynamic
33%
Case Study
33%
Real Time Performance
33%
Person Re-Identification
33%
Complex Background
33%
Segmentation Method
33%
World Application
33%
3d Reconstruction
33%
Postprocessing
33%
Interaction Quality
33%
Project Outcome
33%
Convolutional Network
33%
Convolutional Neural Network
33%
Computer Vision
33%
Captured Image
33%
Segmentation Performance
33%
segmentation accuracy
33%
Action Recognition
33%
Detection Accuracy
26%
Feature Dimension
22%
Detection Result
16%
Inference Model
16%
Human-Computer Interaction
16%
Concatenation Operation
11%
Multiple Network
11%
Visual Informations
11%
Validation Set
11%
Fusion Technique
11%
Facial Feature
11%
Detection Performance
11%
Enhance Performance
11%
Spatial Resolution
9%
Annotation
9%
Decision Tree Algorithm
8%
Structural Dimension
8%
