Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network.
Linwei YeMrigank RochanZhi LiuXiaoqin ZhangYang WangPublished in: CoRR (2021)
Keyphrases
- cross modal
- perceptual information
- image analysis
- visual data
- test images
- image regions
- image data
- multi modal
- image classification
- image database
- image features
- image retrieval
- image annotation
- visual similarity
- input image
- object recognition
- image segmentation
- spatial information
- image collections
- similarity measure
- visual attention
- image set
- feature space