A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation.
Naiyu FangLemiao QiuShuyou ZhangZili WangKerui HuKang WangPublished in: CoRR (2023)
Keyphrases
- semantic segmentation
- street scenes
- label transfer
- conditional random fields
- superpixels
- weakly supervised
- scene classification
- object categories
- eye movements
- multiple views
- object classes
- visual attention
- pascal voc
- eye tracking
- scale space
- object class
- object detection
- bayesian networks
- segmentation algorithm
- markov random field
- input image