X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer.
Linglin JingYing XueXu YanChaoda ZhengDong WangRuimao ZhangZhigang WangHui FangBin ZhaoZhen LiPublished in: AAAI (2024)
Keyphrases
- knowledge transfer
- scene understanding
- cross modal
- video surveillance
- multi modal
- object detection
- vision system
- object recognition
- d scene
- knowledge sharing
- transfer learning
- visual data
- computer vision
- video frames
- video sequences
- image retrieval
- background subtraction
- event detection
- learning tasks
- moving objects
- multi class
- machine learning
- key frames
- multimedia databases
- machine learning algorithms
- decision trees
- text classification
- information retrieval