Multimodal Transformer for Automatic 3D Annotation and Object Detection.
Chang LiuXiaoyan QianBinxiao HuangXiaojuan QiEdmund Y. LamSiew-Chong TanNgai WongPublished in: CoRR (2022)
Keyphrases
- object detection
- manual annotation
- automatic annotation
- semi automatic
- automatic indexing
- labor intensive
- multi modal
- fully automatic
- semantic annotation
- object categories
- semi automatically
- computer vision
- human detection
- fuzzy logic
- active learning
- face detection
- object recognition
- metadata
- hand crafted
- scene recognition
- machine learning
- automatic image annotation
- object class
- pedestrian detection
- wordnet
- multi class
- feature selection
- artificial intelligence