PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning.
Amir RasouliIuliia KotserubaPublished in: ICRA (2023)
Keyphrases
- cross modal
- multitask learning
- multi modal
- multi task
- gaussian processes
- learning tasks
- multi task learning
- semi supervised
- visual similarity
- multimedia retrieval
- image retrieval
- image sequences
- supervised learning
- text mining
- object detection
- machine learning
- pedestrian detection
- active learning
- spatio temporal
- visual recognition