Retrieval of TV Talk-Show Speakers by Associating Audio Transcript to Visual Clusters.
Yina HanShanghuan SongWeikang ZhaoPublished in: IEEE Access (2017)
Keyphrases
- cross modal
- visual information
- lifelog
- content based video retrieval
- visual data
- video indexing and retrieval
- multimedia information
- visual features
- speech recognition
- image retrieval
- multi modal
- hierarchical clustering
- multimedia databases
- medical image retrieval
- clustering algorithm
- video shots
- multimedia
- information retrieval
- audio visual content
- audio visual
- data points
- relevance feedback
- visual similarity
- image database
- document retrieval
- content based retrieval
- information retrieval systems
- visual concepts
- video search
- visual and textual features
- high level
- audio features
- multimedia information retrieval
- visual appearance
- multimedia documents
- semantic content
- query expansion
- news video
- speaker identification
- low level
- semantically relevant
- visual content
- closed captions
- test collection
- eye movements