Cross-modal alignment and translation for missing modality action recognition.
Yeonju ParkSangmin WooSumin LeeMuhammad Adi NugrohoChangick KimPublished in: Comput. Vis. Image Underst. (2023)
Keyphrases
- action recognition
- cross modal
- multi modal
- activity recognition
- bag of words
- human actions
- computer vision
- visual recognition
- human activities
- image retrieval
- visual similarity
- multimedia retrieval
- multimedia databases
- visual data
- high dimensional
- image annotation
- visual words
- bag of features
- object recognition
- image sequences