Deep Multimodal Fusion for Generalizable Person Re-identification.
Suncheng XiangHao ChenJingsheng GaoSijia DuJiawang MouTing LiuDahong QianYuzhuo FuPublished in: CoRR (2022)
Keyphrases
- person re identification
- multimodal fusion
- high robustness
- relevance feedback
- metric learning
- audio visual
- multimodal interfaces
- video surveillance
- sparse coding
- gait recognition
- camera network
- feature representation
- distance metric
- human computer interaction
- riemannian manifolds
- sparse representation
- three dimensional
- visual features
- multi modal
- pairwise
- feature space
- training data
- face recognition