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: IEEE Trans. Intell. Transp. Syst. (2024)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- superpixels
- scene classification
- label transfer
- weakly supervised
- object categories
- eye movements
- multiple views
- visual attention
- object class
- image understanding
- pascal voc
- scale space
- object segmentation
- object detection
- viewpoint
- long range
- higher order
- information extraction
- image set
- eye tracking
- learning algorithm