Referring Segmentation in Images and Videos With Cross-Modal Self-Attention Network.
Linwei YeMrigank RochanZhi LiuXiaoqin ZhangYang WangPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2022)
Keyphrases
- cross modal
- perceptual information
- image analysis
- test images
- image data
- input image
- visual data
- image retrieval
- image database
- image regions
- visual similarity
- multi modal
- image segmentation
- image classification
- video sequences
- spatial information
- image set
- image understanding
- object recognition
- multiscale
- visual information
- image collections
- image features