Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding.
Hassan AkbariSvebor KaramanSurabhi BhargavaBrian ChenCarl VondrickShih-Fu ChangPublished in: CVPR (2019)
Keyphrases
- semantic space
- image data
- multiscale
- image content
- image classification
- image pixels
- image features
- cross modal
- image regions
- similarity measure
- unsupervised manner
- multi modal
- image retrieval
- spatial information
- image representation
- mapping function
- image set
- visual data
- semantic concepts
- semantic features
- semantically meaningful
- keywords
- clustering algorithm