Multimodal Transformer for Automatic 3D Annotation and Object Detection.
Chang LiuXiaoyan QianBinxiao HuangXiaojuan QiEdmund Y. LamSiew-Chong TanNgai WongPublished in: ECCV (38) (2022)
Keyphrases
- object detection
- manual annotation
- automatic annotation
- automatic indexing
- fuzzy logic
- semi automatically
- active learning
- fully automatic
- computer vision
- object class
- image retrieval
- face detection
- object categories
- metadata
- scene understanding
- genetic algorithm
- hand crafted
- power transformers
- incipient fault
- audio visual
- image annotation
- background subtraction
- multimedia
- knowledge base