Aerial Recognition


Overview

Image and video analysis of aerial scenes is crucial in a myriad of real life applications such as surveillance, search and rescue mapping, satellite imagery, etc. The GAMMA group is working towards artificial intelligence based solutions for problems related to aerial scenes analysis. Our research areas include aerial video activity recognition, memory efficient neural networks, synthetic data augmentation and transfer learning, synthetic data generation, and geo-localization from aerial point cloud.

Publications

Project Conference/Journal Year
SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining arxiv 2024
UAVMAE: Object-Aware Masked Autoencoding for Self-Supervised UAV Video Pretraining arxiv 2024
AGL-Net: Aerial-Ground Cross-Modal Global Localization with Varying Scales arxiv 2024
HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View arxiv 2024
PLAR: Prompt Learning for Action Recognition Arxiv 2024
UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception ICRA 2024
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition WACV 2024
MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition WACV 2024
Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models Siggraph Asia 2023
CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition ICCV 2023
DIFFAR: Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition ICRA 2023
AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning ICRA 2023
FAR: Fourier Aerial Video Recognition ECCV 2022