# Neural Spatial-Temporal Tensor Representation for Infrared Small Target Detection

arXiv: https://arxiv.org/abs/2412.17302 · HTML: https://mlsanity.com/paper/2412.17302/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2024.

## Built on by (most cited first, 5 of 5)

- [Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives](https://mlsanity.com/paper/2505.15222/) (2025)
- [Motion-Enhanced Nonlocal Similarity Implicit Neural Representation for Infrared Dim and Small Target Detection](https://mlsanity.com/paper/2504.15665/) (2025)
- [Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain](https://mlsanity.com/paper/2604.01934/) (2026)
- [Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets](https://mlsanity.com/paper/2607.16007/) (2026)
- [DISTA-Net++: Rethinking Infrared Small Target Unmixing Beyond Sub-Pixel Separation](https://mlsanity.com/paper/2609.18773/) (2026)

## Abstract (arXiv)

Optimization-based approaches dominate infrared small target detection as they leverage infrared imagery's intrinsic low-rankness and sparsity. While effective for single-frame images, they struggle with dynamic changes in multi-frame scenarios as traditional spatial-temporal representations often fail to adapt. To address these challenges, we introduce a Neural-represented Spatial-Temporal Tensor (NeurSTT) model. This framework employs nonlinear networks to enhance spatial-temporal feature correlations in background approximation, thereby supporting target detection in an unsupervised manner. Specifically, we employ neural layers to approximate sequential backgrounds within a low-rank informed deep scheme. A neural three-dimensional total variation is developed to refine background smoothness while reducing static target-like clusters in sequences. Traditional sparsity constraints are incorporated into the loss functions to preserve potential targets. By replacing complex solvers with a deep updating strategy, NeurSTT simplifies the optimization process in a domain-awareness way. Visual and numerical results across various datasets demonstrate that our method outperforms detection challenges. Notably, it has 16.6× fewer parameters and averaged 19.19% higher in IoU compared to the suboptimal method on 256 × 256 sequences.