Joint embeddings with multimodal cues for video-text retrieval.
Niluthpol Chowdhury MithunJuncheng LiFlorian MetzeAmit K. Roy-ChowdhuryPublished in: Int. J. Multim. Inf. Retr. (2019)
Keyphrases
- text retrieval
- multimodal fusion
- multimedia
- visual cues
- information retrieval
- document collections
- multiple modalities
- inverted file
- cross language
- multimedia retrieval
- multimedia information retrieval
- retrieval systems
- query expansion
- video data
- document retrieval
- latent semantic indexing
- video content
- retrieval model
- multi modal
- image retrieval
- video frames
- automatic query expansion
- key frames
- low dimensional
- video sequences
- blind relevance feedback
- space time
- low level
- retrieval quality
- test collection
- mid level
- video search
- digital libraries