- row-wise and column-wise LSTM on feature map: [1]
- graph LSTM on superpixels: [2]
- 3D graph: [3]
- DAG on feature map: [4]
Reference
- Li, Zhen, et al. “Lstm-cf: Unifying context modeling and fusion with lstms for rgb-d scene labeling.” ECCV, 2016.
- Liang, Xiaodan, et al. “Semantic object parsing with graph lstm.” ECCV, 2016.
- Qi, Xiaojuan, et al. “3d graph neural networks for rgbd semantic segmentation. ICCV, 2017.
- Ding, Henghui, et al. “Boundary-aware feature propagation for scene segmentation.” ICCV, 2019.