Convolutional Neural Networks or Vision Transformers: Who Will Win the Race for Action Recognitions in Visual Data?
Oumaima MoutikHiba SekkatSmail TiganiAbdellah ChehriRachid SaadaneTaha Ait TchakouchtAnand PaulPublished in: Sensors (2023)
Keyphrases
- visual data
- convolutional neural networks
- human actions
- visual information
- action recognition
- visual features
- computer vision
- human motion
- multimedia data
- high dimensional data
- image data
- video sequences
- contextual information
- image processing
- video data
- visual content
- image content
- human activities
- image sequences
- image classification
- data mining
- human body
- space time
- image retrieval
- search engine
- information retrieval