MHAiR: A Dataset of Audio-Image Representations for Multimodal Human Actions.
Muhammad Bilal ShaikhDouglas ChaiSyed Mohammed Shamsul IslamNaveed AkhtarPublished in: Data (2024)
Keyphrases
- human actions
- image representation
- action recognition
- visual data
- bag of words
- spatio temporal
- audio visual
- image classification
- visual features
- human motion
- multiscale
- human activities
- object recognition
- video sequences
- space time
- visual information
- image content
- image retrieval
- activity recognition
- recognition of human actions
- feature representations
- action sequences
- image features
- recognizing actions
- feature space
- bag of features
- visual words
- scene classification
- computer vision
- action recognition in videos
- human body
- image sequences
- low level features
- semi supervised
- d objects
- feature extraction
- high level