Abstractive Text-Image Summarization Using Multi-Modal Attentional Hierarchical RNN.
Jingqiang ChenHai ZhugePublished in: EMNLP (2018)
Keyphrases
- multi modal
- multiple modalities
- video search
- image data
- uni modal
- auto annotation
- image annotation
- image features
- input image
- image classification
- image analysis
- web images
- image collections
- multi modality
- fusing multiple
- segmentation method
- image content
- image representation
- audio visual
- cross modal
- multiscale
- image segmentation
- image regions
- image processing
- high dimensional
- recurrent neural networks
- semantic concepts
- low level
- high resolution
- image retrieval
- high level