Transforming Visual Scene Graphs to Image Captions.
Xu YangJiawei PengZihua WangHaiyang XuQinghao YeChenliang LiMing YanFei HuangZhangzikang LiYu ZhangPublished in: CoRR (2023)
Keyphrases
- visual scene
- image data
- input image
- single image
- multiscale
- image representation
- image analysis
- image segmentation
- complex scenes
- image collections
- image features
- image classification
- image matching
- image content
- image retrieval
- vision system
- object recognition
- keypoints
- image regions
- low level
- multi modal
- image understanding