Distance metric learning (DML) is to learn the embeddings where examples from the same
class are closer than examples from different classes. It can be cast as an optimization …

Learning the distance metric between pairs of examples is of great importance for learning
and visual recognition. With the remarkable success from the state of the art convolutional …

Distance metric learning (DML) has been successfully applied to object classification, both
in the standard regime of rich training data and in the few-shot scenario, where each …

Fine-grained image classification is to recognize hundreds of subcategories belonging to
the same basic-level category, such as 200 subcategories belonging to the bird, which is …

We suggest a new loss for learning deep embeddings. The key characteristics of the new
loss is the absence of tunable parameters and very good results obtained across a range of …

We propose a simple and straightforward way of creating powerful image representations
via cross-dimensional weighting and aggregation of deep convolutional neural network …

The widespread use of surveillance cameras toward smart and safe cities poses the critical
but challenging problem of vehicle reidentification (Re-ID). The state-of-the-art research …

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field
of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to …

Deep neural networks require a large amount of labeled training data during supervised
learning. However, collecting and labeling so much data might be infeasible in many cases …

We have witnessed rapid evolution of deep neural network architecture design in the past
years. These latest progresses greatly facilitate the developments in various areas such as …