Segment beyond View: Handling Partially Missing Modality for Audio-Visual Semantic Segmentation.
Renjie WuHu WangFeras DayoubHsiang-Ting ChenPublished in: AAAI (2024)
Keyphrases
- audio visual
- semantic segmentation
- multi modal
- superpixels
- conditional random fields
- visual information
- weakly supervised
- visual data
- multimedia
- scene classification
- input image
- data sets
- object categories
- multiscale
- three dimensional
- visual features
- segmentation algorithm
- facial expressions
- object classes
- object segmentation