Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives.
Sheng LuoWei ChenWanxin TianRui LiuLuanxuan HouXiubao ZhangHaifeng ShenRuiqi WuShuyi GengYi ZhouLing ShaoYi YangBojun GaoQun LiGuobin WuPublished in: CoRR (2024)
Keyphrases
- multi modal
- multi task
- multi task learning
- scene understanding
- learning tasks
- multiple tasks
- learning problems
- learning algorithm
- sparse learning
- learning models
- multi modality
- video surveillance
- real time
- reinforcement learning
- object recognition
- high dimensional
- learning process
- object detection
- prior knowledge
- probabilistic model
- medical images
- d scene
- gaussian processes
- transfer learning
- vision system
- image processing