Video Captioning Based on Joint Image-Audio Deep Learning Techniques.
Chien-Yao WangPei-Sin LiawKai-Wen LiangJia-Ching WangPao-Chi ChangPublished in: ICCE-Berlin (2019)
Keyphrases
- deep learning
- video files
- image features
- multiscale
- single image
- image classification
- image segmentation
- input image
- image representation
- image content
- image retrieval
- high resolution
- video data
- key frames
- machine learning
- segmentation algorithm
- video sequences
- region of interest
- image processing
- information extraction
- segmentation method
- test images
- lighting conditions
- image sequences