Image-to-video person re-identification with cross-modal embeddings.
Zhongwei XieLin LiXian ZhongLuo ZhongJianwen XiangPublished in: Pattern Recognit. Lett. (2020)
Keyphrases
- cross modal
- visual data
- person re identification
- image retrieval
- image data
- input image
- multiscale
- image classification
- image features
- video data
- image representation
- image content
- low level
- similarity measure
- multimedia
- multi modal
- visual recognition
- visual features
- spatial information
- vector space
- image collections
- web images
- visual similarity
- object recognition
- natural images
- space time
- keypoints
- image database