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: CoRR (2023)
Keyphrases
- multi modal
- multi view
- multi tasking
- single view
- operating system
- depth map
- computer vision
- d objects
- three dimensional
- multiple views
- high dimensional
- range images
- multi view learning
- multi view clustering
- multi modality
- vision system
- semi supervised
- surface reconstruction
- virtual machine
- multi view images
- multi view reconstruction
- cross modal
- free viewpoint
- image processing
- semi supervised learning
- visual hull
- feature extraction
- multi view face detection
- uni modal