End-to-end image captioning based on reduced feature maps of deep learners pre-trained for object detection.
Yan LyuQiangfu ZhaoYong LiuPublished in: RACS (2022)
Keyphrases
- end to end
- pre trained
- object detection
- feature maps
- input image
- image data
- training data
- image features
- multiscale
- image retrieval
- image segmentation
- low level
- training examples
- high resolution
- image classification
- neural network
- image quality
- decision trees
- control signals
- lighting conditions
- image representation
- learning process