We propose to address the problem of few-shot classification by meta-learning" what to
observe" and" where to attend" in a relational perspective. Our method leverages relational …

We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic
correspondence. To robustly match points among different instances within the same object …

Image registration is a crucial step for remote sensing image processing. Automatic
registration of multispectral remote sensing images could be challenging due to the …

Despite significant progress in machine learning, pedestrian detection in the real-world is
still regarded as one of the challenging problems, limited by occluded appearances …

Spatio-temporal convolution often fails to learn motion dynamics in videos and thus an
effective motion representation is required for video understanding in the wild. In this paper …

Establishing dense visual correspondence between multiple images is a fundamental task
in many applications of computer vision and computational photography. Classical …

Robust, well-distributed and accurate feature matching in multi-sensor remote sensing
image is a difficult task duo to significant geometric and illumination differences. In this …

Medical image analysis methods have been applied to clinical scenarios of tumor diagnosis
and treatment. Many studies have attempted to optimize the effectiveness of tumor MRI …

When dealing with the registration of information from different image sources, the de facto
similarity measure used is Mutual Information (MI). Although MI gives good performance in …

The joint analysis of thermal and visible light images of plants can help to increase the
accuracy of early disease detection. Registration of thermal and visible light images is an …