MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning.
Sonia BaeeErfan PakdamanianInki KimLu FengVicente OrdonezLaura E. BarnesPublished in: ICCV (2021)
Keyphrases
- maximum entropy
- visual attention
- inverse reinforcement learning
- eye movements
- eye tracking
- saliency map
- preference elicitation
- maximum entropy principle
- vision system
- random fields
- markov models
- higher level
- conditional random fields
- reward function
- artificial intelligence
- real time
- object based visual attention
- information extraction
- dynamic programming
- low level
- data mining