In the last few years, deep learning has led to very good performance on a variety of
problems, such as visual recognition, speech recognition and natural language processing …

Extracting geometric features from 3D scans or point clouds is the first step in applications
such as registration, reconstruction, and tracking. State-of-the-art methods require …

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 …

In this paper we aim to determine the location and orientation of a ground-level query image
by matching to a reference database of overhead (eg satellite) images. For this task we …

We propose a simple, yet powerful regularization technique that can be used to significantly
improve both the pairwise and triplet losses in learning local feature descriptors. The idea is …

Multi-instance point cloud registration is the problem of estimating multiple poses of source
point cloud instances within a target point cloud. Solving this problem is challenging since …

Recent works on 6D object pose estimation focus on learning keypoint correspondences
between images and object models, and then determine the object pose through RANSAC …

How to correctly stress hard samples in metric learning is critical for visual recognition tasks,
especially in challenging person re-ID applications. Pedestrians across cameras with …

The explosive growth of multimedia contents has made hashing an indispensable
component in image retrieval. In particular, learning-based hashing has recently shown …

With emerging demand for large-scale video analysis, the Motion Picture Experts Group
(MPEG) initiated the Compact Descriptor for Video Analysis (CDVA) standardization in 2014 …