Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings.
Zhongwei XieLin LiXian ZhongLuo ZhongPublished in: CoRR (2018)
Keyphrases
- cross modal
- person re identification
- visual data
- image data
- input image
- image content
- image features
- multiscale
- low level
- image classification
- feature representation
- multi modal
- image retrieval
- key frames
- visual similarity
- spatial information
- video surveillance
- image regions
- image representation
- multimedia
- image collections
- video retrieval
- metric learning
- visual content
- object recognition
- visual recognition
- visual concepts
- video sequences