Cross-Modal Transformer for RGB-D semantic segmentation of production workshop objects.
Qingjun RuGuangzhu ChenTingyu ZuoXiaojuan LiaoPublished in: Pattern Recognit. (2023)
Keyphrases
- cross modal
- semantic segmentation
- object classes
- multi modal
- object segmentation
- superpixels
- object categories
- visual data
- object class
- d objects
- bounding box
- conditional random fields
- weakly supervised
- computer vision
- graph cuts
- high dimensional
- natural language processing
- active learning
- image retrieval
- face recognition
- high level