TIM: A Time Interval Machine for Audio-Visual Action Recognition.
Jacob ChalkJaesung HuhEvangelos KazakosAndrew ZissermanDima DamenPublished in: CoRR (2024)
Keyphrases
- action recognition
- audio visual
- human actions
- multi modal
- visual data
- visual information
- bag of words
- activity recognition
- action classification
- recognizing human actions
- computer vision
- multimedia
- multi stream
- human activities
- recognizing actions
- recognition of human actions
- contextual information
- image sequences
- three dimensional
- machine learning