MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses.
Irtiza HasanFrancesco SettiTheodore TsesmelisAlessio Del BueFabio GalassoMarco CristaniPublished in: CoRR (2018)
Keyphrases
- motion patterns
- multi target tracking
- spatio temporal
- image sequences
- recurrent neural networks
- short term
- trajectory data
- motion model
- moving objects
- data association
- crowded scenes
- long term
- object trajectories
- space time
- frontal face
- multiple targets
- motion analysis
- eye gaze
- real time
- appearance model
- video sequences
- motion trajectories
- neural network