Multi-scale Deep Learning Architectures for Person Re-identification
ICCV, pp. 5409-5418, 2017.
We propose a novel multi-scale deep learning model for re-id which aims to learn discriminative feature representations at multiple scales with automatically determined scale weighting for combining them )
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing...More
PPT (Upload PPT)