Enhanced video clustering using multiple riemannian manifold-valued descriptors and audio-visual information.
Wenbo HuHongjian ZhanYinghong TianYujie XiongYue LuPublished in: Expert Syst. Appl. (2024)
Keyphrases
- visual information
- visual data
- visual cues
- visual descriptors
- visual features
- low level
- audio visual
- eye movements
- visual content
- video sequences
- video data
- semantic information
- low level features
- geometric structure
- video retrieval
- video content
- affine invariant
- shape descriptors
- multiscale
- feature vectors
- tangent space