# Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition

arXiv: https://arxiv.org/abs/2510.04282 · HTML: https://mlsanity.com/paper/2510.04282/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [Recurrent Neural Networks (RNNs): A gentle Introduction and Overview](https://mlsanity.com/paper/1912.05911/) (2019)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset](https://mlsanity.com/paper/2002.10152/) (2020)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [Condition-Invariant Multi-View Place Recognition](https://mlsanity.com/paper/1902.09516/) (2019)
- [JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition](https://mlsanity.com/paper/2403.19787/) (2024)
- [Spatio-Temporal Ranked-Attention Networks for Video Captioning](https://mlsanity.com/paper/2001.06127/) (2020)
- [Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition](https://mlsanity.com/paper/2305.11467/) (2023)
- [Leveraging BEV Representation for 360-degree Visual Place Recognition](https://mlsanity.com/paper/2305.13814/) (2023)
- [BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues](https://mlsanity.com/paper/2403.06600/) (2024)
- [Dynamically Modulating Visual Place Recognition Sequence Length For Minimum Acceptable Performance Scenarios](https://mlsanity.com/paper/2407.00863/) (2024)

## Built on by (most cited first, 1 of 1)

- [FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization](https://mlsanity.com/paper/2606.28933/) (2026)

## Abstract (arXiv)

Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length), deliver fast inference, and have low memory usage to meet real-time constraints. However, existing approaches prioritize performance at the expense of flexibility and effi- ciency. To address this gap, we propose Adapt-STformer, a Seq-VPR method built around our novel Recurrent Deformable Transformer Encoder (Recurrent-DTE), which uses an iterative recurrent mechanism to fuse information from multiple sequen- tial frames. This design naturally supports variable seq-lengths, fast inference, and low memory usage. Experiments on the Nordland, Oxford, and NuScenes datasets show that Adapt- STformer boosts recall by up to 17% while reducing sequence extraction time by 36% and lowering memory usage by 35% relative to our best comparable baseline. Our code is released at https://ai4ce.github.io/Adapt-STFormer/.