# GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformers

arXiv: https://arxiv.org/abs/2408.02840 · HTML: https://mlsanity.com/paper/2408.02840/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching](https://mlsanity.com/paper/2005.03860/) (2020)
- [Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image](https://mlsanity.com/paper/2204.04752/) (2022)
- [Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence](https://mlsanity.com/paper/2212.04074/) (2022)
- [Cross-View Image Matching for Geo-localization in Urban Environments](https://mlsanity.com/paper/1703.07815/) (2017)
- [The Transformer Network for the Traveling Salesman Problem](https://mlsanity.com/paper/2103.03012/) (2021)
- [Uncertainty-aware Vision-based Metric Cross-view Geolocalization](https://mlsanity.com/paper/2211.12145/) (2022)
- [Visual Cross-View Metric Localization with Dense Uncertainty Estimates](https://mlsanity.com/paper/2208.08519/) (2022)
- [SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation](https://mlsanity.com/paper/2211.14651/) (2022)
- [Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching](https://mlsanity.com/paper/2203.14148/) (2022)
- [Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation](https://mlsanity.com/paper/2005.11592/) (2020)
- [Convolutional Cross-View Pose Estimation](https://mlsanity.com/paper/2303.05915/) (2023)
- [Cross-View Image Sequence Geo-localization](https://mlsanity.com/paper/2210.14295/) (2022)

## Built on by (most cited first, 10 of 10)

- [Cross-View Image Set Geo-Localization](https://mlsanity.com/paper/2412.18852/) (2024)
- [Spatiotemporal Contrastive Learning for Cross-View Video Localization in Unstructured Off-road Terrains](https://mlsanity.com/paper/2506.05250/) (2025)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [Interpretable Perception and Reasoning for Audiovisual Geolocation](https://mlsanity.com/paper/2603.05708/) (2026)
- [RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization](https://mlsanity.com/paper/2603.27758/) (2026)
- [VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale](https://mlsanity.com/paper/2604.12159/) (2026)
- [SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes](https://mlsanity.com/paper/2608.07835/) (2026)
- [Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery](https://mlsanity.com/paper/2602.14929/) (2026)
- [Trajectory-aware Cross-view Geo-localization with Sequential Observations](https://mlsanity.com/paper/2607.15491/) (2026)
- [X2Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization](https://mlsanity.com/paper/2608.16658/) (2026)

## Abstract (arXiv)

Cross-view video geo-localization (CVGL) aims to derive GPS trajectories from street-view videos by aligning them with aerial-view images. Despite their promising performance, current CVGL methods face significant challenges. These methods use camera and odometry data, typically absent in real-world scenarios. They utilize multiple adjacent frames and various encoders for feature extraction, resulting in high computational costs. Moreover, these approaches independently predict each street-view frame's location, resulting in temporally inconsistent GPS trajectories. To address these challenges, in this work, we propose GAReT, a fully transformer-based method for CVGL that does not require camera and odometry data. We introduce GeoAdapter, a transformer-adapter module designed to efficiently aggregate image-level representations and adapt them for video inputs. Specifically, we train a transformer encoder on video frames and aerial images, then freeze the encoder to optimize the GeoAdapter module to obtain video-level representation. To address temporally inconsistent trajectories, we introduce TransRetriever, an encoder-decoder transformer model that predicts GPS locations of street-view frames by encoding top-k nearest neighbor predictions per frame and auto-regressively decoding the best neighbor based on the previous frame's predictions. Our method's effectiveness is validated through extensive experiments, demonstrating state-of-the-art performance on benchmark datasets. Our code is available at https://github.com/manupillai308/GAReT.