Search Results for author:
Found 8 papers, 2 papers with code
Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification
A lightweight solution using grouped convolution is also proposed to mimic the learning of loss-splitting into multiple embeddings while significantly reducing the model size.
Ranked #1 on
Vehicle Re-Identification
on VeRi-Wild Small
Beyond the Shortest Path : Unsupervised Domain Adaptation by Sampling Subspaces Along the Spline Flow
In this case, the source/target domains are represented in the form of subspaces, which are treated as points on the Grassmann manifold.
Lifting Object Detection Datasets into 3D
In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image.
Fast Training of Pose Detectors in the Fourier Domain
In many datasets, the samples are related by a known image transformation, such as rotation, or a repeatable non-rigid deformation.
Reconstructing PASCAL VOC
We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations.
Non-Parametric Bayesian Constrained Local Models
This work presents a novel non-parametric Bayesian formulation for aligning faces in unseen images.
High-Speed Tracking with Kernelized Correlation Filters
Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers.
Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem
In the past few years there has been a growing interest on geometric frameworks to learn supervised classification models on Riemannian manifolds [31, 27].
