EgoCap and EgoFormer: First-person image captioning with context fusion.
Zhuangzhuang DaiVu TranAndrew MarkhamNiki TrigoniM. Arif RahmanLahiru N. S. WijayasinghaJohn A. StankovicChen LiPublished in: Pattern Recognit. Lett. (2024)
Keyphrases
- image content
- image data
- input image
- image features
- single image
- multiscale
- image classification
- image segmentation
- segmentation method
- image retrieval
- image collections
- template matching
- image matching
- image representation
- grey level
- fusion method
- edge detection
- low level
- image analysis
- contextual information
- feature points
- image regions
- spatial information
- image database
- image pixels
- keypoints
- hough transform
- test images
- optical flow
- information fusion
- image structure
- similarity measure