Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation.
Bowen WangLiangzhi LiYuta NakashimaRyo KawasakiHajime NagaharaYasushi YagiPublished in: IEEE Access (2021)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- label transfer
- video sequences
- scene classification
- conditional random fields
- video data
- weakly supervised
- object categories
- video frames
- segmentation algorithm
- object class
- object recognition
- multiscale
- natural images
- hidden markov models
- image understanding
- higher order