Parallel-fusion LSTM with synchronous semantic and visual information for image captioning.
Jing ZhangKangkang LiZhe WangPublished in: J. Vis. Commun. Image Represent. (2021)
Keyphrases
- visual information
- image collections
- low level
- visual data
- visual cues
- content based image
- low level visual features
- visual features
- visual descriptors
- visual similarity
- image classification
- semantic information
- image data
- image content
- visual content
- low level features
- multiscale
- textual information
- high level
- visual concepts
- semantic gap
- image representation
- visual and textual information
- multi sensor
- semantic context
- image retrieval
- image features
- visual input
- human visual system
- semantic concepts
- visual perception
- image set
- visual scene
- audio visual
- visual information retrieval
- video retrieval
- image quality assessment
- web images
- eye movements
- image search
- machine learning
- content based image retrieval systems
- object recognition
- image processing