Cross-Modal Retrieval With CNN Visual Features: A New Baseline.
Yunchao WeiYao ZhaoCanyi LuShikui WeiLuoqi LiuZhenfeng ZhuShuicheng YanPublished in: IEEE Trans. Cybern. (2017)
Keyphrases
- visual features
- cross modal
- visual similarity
- image retrieval
- visual data
- visual content
- visual information
- semantic concepts
- multi modal
- image classification
- multimedia retrieval
- image search
- web images
- image annotation
- low level features
- image database
- low level
- keywords
- image collections
- low level visual features
- semantic content
- multimedia databases
- cbir systems
- bag of features
- higher level
- relevance feedback
- text retrieval
- semantic gap
- key frames
- bag of words
- video sequences
- high level
- image processing
- information retrieval