Towards Multimodal Understanding of Passenger-Vehicle Interactions in Autonomous Vehicles: Intent/Slot Recognition Utilizing Audio-Visual Data.
Eda OkurShachi H. KumarSaurav SahayLama NachmanPublished in: CoRR (2019)
Keyphrases
- visual data
- autonomous vehicles
- audio visual
- multimodal information
- visual information
- path planning
- visual features
- obstacle avoidance
- high dimensional
- contextual information
- pattern recognition
- multiagent systems
- robot control
- video data
- autonomous agents
- visual content
- multimedia data
- object recognition
- video sequences
- image data
- dynamic environments
- activity recognition
- traffic light
- high dimensional data
- real time
- multi modal
- mobile robot
- multimedia
- image content
- human motion
- human actions
- text data
- low level
- image retrieval
- feature extraction
- image sequences
- neural network