Actor-Action Semantic Segmentation with Region Masks.
Kang DangChunluan ZhouZhigang TuMichael HoyJustin DauwelsJunsong YuanPublished in: CoRR (2018)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- label transfer
- object categories
- scene classification
- conditional random fields
- weakly supervised
- object class
- bounding box
- input image
- object detection
- object classes
- pascal voc
- region of interest
- computer vision
- image set
- object segmentation
- image understanding
- d objects
- object recognition