No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration.
José Vargas QuirosLaura Cabrera QuirosHayley HungPublished in: CoRR (2022)
Keyphrases
- visual information
- cross modal
- multimedia
- visual data
- lifelog
- filtering algorithm
- pose estimation
- visual analysis
- thermal images
- false positives
- partial occlusion
- detection method
- detection algorithm
- anomaly detection
- video recordings
- d objects
- low level
- high level
- activity recognition
- object detection
- detection rate
- ubiquitous computing
- position and orientation
- augmented reality
- ambient intelligence
- cluttered background
- visual features
- sensor networks
- object recognition