Segment Beyond View: Handling Partially Missing Modality for Audio-Visual Semantic Segmentation.
Renjie WuHu WangFeras DayoubHsiang-Ting ChenPublished in: CoRR (2023)
Keyphrases
- audio visual
- semantic segmentation
- multi modal
- superpixels
- conditional random fields
- visual information
- weakly supervised
- scene classification
- multimedia
- object categories
- visual data
- object classes
- object recognition
- segmentation method
- image understanding
- image annotation
- bounding box
- information extraction
- video sequences
- multiscale
- information retrieval