Composite Correlation Quantization for Efficient Multimodal Retrieval
SIGIR, pp. 579-588, 2016.
Efficient similarity retrieval from large-scale multimodal database is pervasive in modern search engines and social networks. To support queries across content modalities, the system should enable cross-modal correlation and computation-efficient indexing. While hashing methods have shown great potential in achieving this goal, current a...More
PPT (Upload PPT)