In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different view-points.
Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i. e. the relations between local features, while ignoring the heterogeneous correlation of local features in different modalities.
To these ends, we propose a simpler but more effective Deep Fusion Generative Adversarial Networks (DF-GAN).
Ranked #4 on Text-to-Image Generation on CUB
Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution.
Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure.
However, the number of labeled source samples are always limited due to expensive annotation cost in practice, making sub-optimal performance been observed.
It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations.
Cross-view classification that means to classify samples from heterogeneous views is a significant yet challenging problem in computer vision.
We present a novel cross-view classification algorithm where the gallery and probe data come from different views.
In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD^2L) approach for SR person re-identification.