EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition.
Evangelos KazakosArsha NagraniAndrew ZissermanDima DamenPublished in: ICCV (2019)
Keyphrases
- action recognition
- audio visual
- activity recognition
- video summarization
- multimodal fusion
- person authentication
- multi modal
- human actions
- motion history images
- bag of words
- visual information
- visual data
- spatio temporal
- computer vision
- action classification
- multimedia
- multi stream
- temporal information
- recognizing human actions
- human activities
- space time
- machine learning
- action recognition in videos
- atomic actions
- spatial and temporal
- eye movements
- feature space
- object recognition
- metadata
- recognition of human actions