Cross-modal Moment Localization in Videos.
Meng LiuXiang WangLiqiang NieQi TianBaoquan ChenTat-Seng ChuaPublished in: ACM Multimedia (2018)
Keyphrases
- cross modal
- multi modal
- visual data
- multimedia retrieval
- visual recognition
- perceptual information
- video sequences
- image retrieval
- video data
- video frames
- semantic concepts
- visual similarity
- video content
- video analysis
- human activities
- multimedia
- multimedia databases
- key frames
- image classification
- low level
- feature space
- similarity measure
- image sequences