Transforming Visual Scene Graphs to Image Captions.
Xu YangJiawei PengZihua WangHaiyang XuQinghao YeChenliang LiSongfang HuangFei HuangZhangzikang LiYu ZhangPublished in: ACL (1) (2023)
Keyphrases
- visual scene
- image data
- single image
- input image
- complex scenes
- image features
- image representation
- multiscale
- image retrieval
- image collections
- image analysis
- image classification
- image segmentation
- vision system
- spatial relations
- real time
- similarity measure
- high resolution
- visual features
- higher level
- machine learning