# Cross Spatial Temporal Fusion Attention for Remote Sensing Object Detection via Image Feature Matching

arXiv: https://arxiv.org/abs/2507.19118 · HTML: https://mlsanity.com/paper/2507.19118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [ContextDesc: Local Descriptor Augmentation with Cross-Modality Context](https://mlsanity.com/paper/1904.04084/) (2019)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects](https://mlsanity.com/paper/1911.06283/) (2019)
- [Beyond Cartesian Representations for Local Descriptors](https://mlsanity.com/paper/1908.05547/) (2019)
- [Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity](https://mlsanity.com/paper/2103.16871/) (2021)
- [Domain-Size Pooling in Local Descriptors: DSP-SIFT](https://mlsanity.com/paper/1412.8556/) (2014)
- [A Robust Multimodal Remote Sensing Image Registration Method and System Using Steerable Filters with First- and Second-order Gradients](https://mlsanity.com/paper/2202.13347/) (2022)

## Abstract (arXiv)

Effectively describing features for cross-modal remote sensing image matching remains a challenging task due to the significant geometric and radiometric differences between multimodal images. Existing methods primarily extract features at the fully connected layer but often fail to capture cross-modal similarities effectively. We propose a Cross Spatial Temporal Fusion (CSTF) mechanism that enhances feature representation by integrating scale-invariant keypoints detected independently in both reference and query images. Our approach improves feature matching in two ways: First, by creating correspondence maps that leverage information from multiple image regions simultaneously, and second, by reformulating the similarity matching process as a classification task using SoftMax and Fully Convolutional Network (FCN) layers. This dual approach enables CSTF to maintain sensitivity to distinctive local features while incorporating broader contextual information, resulting in robust matching across diverse remote sensing modalities. To demonstrate the practical utility of improved feature matching, we evaluate CSTF on object detection tasks using the HRSC2016 and DOTA benchmark datasets. Our method achieves state-of-theart performance with an average mAP of 90.99% on HRSC2016 and 90.86% on DOTA, outperforming existing models. The CSTF model maintains computational efficiency with an inference speed of 12.5 FPS. These results validate that our approach to crossmodal feature matching directly enhances downstream remote sensing applications such as object detection.