Using Aesthetics and Action Recognition-Based Networks for the Prediction of Media Memorability.
Mihai Gabriel ConstantinChen KangGabriela DinuFrédéric DufauxGiuseppe ValenziseBogdan IonescuPublished in: MediaEval (2019)
Keyphrases
- motion recognition
- human actions
- action recognition
- activity recognition
- action classification
- bag of words
- spatial temporal
- computer vision
- recognition of human actions
- human detection
- recognizing human actions
- static images
- human activities
- human pose
- body parts
- view invariant
- multimedia
- video sequences
- machine learning
- action primitives
- action recognition in videos
- depth sensors
- depth cameras
- bag of features
- independent component analysis
- user interface