AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception.
Dingkang YangShuai HuangZhi XuZhenpeng LiShunli WangMingcheng LiYuzheng WangYang LiuKun YangZhaoyu ChenYan WangJing LiuPeixuan ZhangPeng ZhaiLihua ZhangPublished in: ICCV (2023)
Keyphrases
- multi modal
- multi view
- multi tasking
- single view
- depth map
- multiple views
- three dimensional
- operating system
- d objects
- multi modality
- computer vision
- range images
- image processing
- multi view reconstruction
- vision system
- virtual machine
- semi supervised
- surface reconstruction
- view synthesis
- multi view learning
- high dimensional
- multi view images
- multi view clustering
- humanoid robot
- text classification
- cross modal
- uni modal