Deep generative cross-modal on-body accelerometer data synthesis from videos.
Shibo ZhangNabil AlshurafaPublished in: UbiComp/ISWC Adjunct (2020)
Keyphrases
- cross modal
- accelerometer data
- activity recognition
- multi modal
- human activities
- behavior recognition
- visual data
- generative model
- image retrieval
- video sequences
- human body
- video frames
- human actions
- visual recognition
- multimedia retrieval
- visual similarity
- multimedia databases
- video data
- video content
- semantic concepts
- video analysis
- computer vision