Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation.
Jungbeom LeeEunji KimSungmin LeeJangho LeeSungroh YoonPublished in: CoRR (2019)
Keyphrases
- weakly supervised
- semantic segmentation
- superpixels
- topic models
- object class
- conditional random fields
- semi supervised
- relation extraction
- input image
- video frames
- named entities
- information retrieval
- key frames
- object categories
- scene classification
- spatial information
- image regions
- text mining
- information extraction
- feature extraction