Joint Deep Exploitation of Semantic Keywords and Visual Features for Malicious Crowd Image Classification.
Joel LevisHyungtae LeeHeesung KwonJames MichaelisMichael KolodnySungmin EumPublished in: CoRR (2016)
Keyphrases
- visual features
- image classification
- semantic concepts
- semantic features
- low level features
- keywords
- semantic content
- bridge the semantic gap
- semantic gap
- visual content
- visual information
- low level visual features
- image features
- bag of words
- image search
- image representation
- semantic information
- bag of features
- visual appearance
- image collections
- visual similarity
- web images
- image annotation
- probabilistic latent semantic analysis
- semantically related
- key frames
- visual words
- semantic relationships
- search engine
- feature extraction
- high level
- global features
- automatic image annotation
- multi label
- feature vectors
- keypoints
- cbir systems
- bag of visual words
- web pages
- computer vision