Search Results for author: Jiuhong Xiao

Found 4 papers, 1 papers with code

Visual Geo-localization with Self-supervised Representation Learning

no code implementations31 Jul 2023 Jiuhong Xiao, Gao Zhu, Giuseppe Loianno

In this work, we present a novel unified VG-SSL framework with the goal to enhance performance and training efficiency on a large VG dataset by SSL methods.

Representation Learning Self-Supervised Learning

Long-range UAV Thermal Geo-localization with Satellite Imagery

1 code implementation5 Jun 2023 Jiuhong Xiao, Daniel Tortei, Eloy Roura, Giuseppe Loianno

This paper proposes a novel thermal geo-localization framework using satellite RGB imagery, which includes multiple domain adaptation methods to address the limited availability of paired thermal and satellite images.

Domain Adaptation Visual Place Recognition

Identity Preserving Loss for Learned Image Compression

no code implementations22 Apr 2022 Jiuhong Xiao, Lavisha Aggarwal, Prithviraj Banerjee, Manoj Aggarwal, Gerard Medioni

We present a novel Identity Preserving Reconstruction (IPR) loss function which achieves Bits-Per-Pixel (BPP) values that are ~38% and ~42% of CRF-23 HEVC compression for LFW (low-resolution) and CelebA-HQ (high-resolution) datasets, respectively, while maintaining parity in recognition accuracy.

Image Compression

Multi-Robot Collaborative Perception with Graph Neural Networks

no code implementations5 Jan 2022 Yang Zhou, Jiuhong Xiao, Yue Zhou, Giuseppe Loianno

Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents.

Decision Making Monocular Depth Estimation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.