Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation.
Bowen WangLiangzhi LiYuta NakashimaRyo KawasakiHajime NagaharaYasushi YagiPublished in: CoRR (2020)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- label transfer
- conditional random fields
- video data
- weakly supervised
- scene classification
- video sequences
- video frames
- dynamic textures
- object categories
- object class
- pascal voc
- object recognition
- object classes
- image understanding
- pixel level
- multiscale
- object segmentation
- long range
- biologically inspired
- higher order
- co occurrence
- object detection