Deep Convolutional Neural Networks (DCNNs) are hard and time-consuming t...
Few-shot learning (FSL) has attracted increasing attention in recent yea...
Most state-of-the-art person re-identification (re-id) methods depend on...
Knowledge distillation is an effective approach to transferring knowledg...
Valuable training data is often owned by independent organizations and
l...
We consider the problem of person search in unconstrained scene images.
...
Knowledge distillation is effective to train small and generalisable net...
Identity alignment models assume precisely annotated images manually. Hu...