# Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition

arXiv: https://arxiv.org/abs/2305.11467 · HTML: https://mlsanity.com/paper/2305.11467/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 15 of 15)

- [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)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [Convolutional Neural Network-based Place Recognition](https://mlsanity.com/paper/1411.1509/) (2014)
- [Spatio-Temporal Representation Factorization for Video-based Person Re-Identification](https://mlsanity.com/paper/2107.11878/) (2021)
- [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)
- [Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations](https://mlsanity.com/paper/2001.08434/) (2020)

## Built on by (most cited first, 6 of 6)

- [JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition](https://mlsanity.com/paper/2403.19787/) (2024)
- [UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2512.21078/) (2025)
- [Collaborative Visual Place Recognition through Federated Learning](https://mlsanity.com/paper/2404.13324/) (2024)
- [Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition](https://mlsanity.com/paper/2510.04282/) (2025)
- [Text2Graph VPR: A Text-to-Graph Expert System for Explainable Place Recognition in Changing Environments](https://mlsanity.com/paper/2512.18613/) (2025)
- [TRAIL: Trajectory-Aware Visual Place Recognition against Unordered Databases](https://mlsanity.com/paper/2609.07373/) (2026)

## Abstract (arXiv)

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are proposed. These methods are either based on matching between frame sequences or extracting sequence descriptors for direct retrieval. However, the former is usually based on the assumption of constant velocity, which is difficult to hold in practice, and is computationally expensive and subject to sequence length. Although the latter overcomes these problems, existing sequence descriptors are constructed by aggregating features of multiple frames only, without interaction on temporal information, and thus cannot obtain descriptors with spatio-temporal discrimination.In this paper, we propose a sequence descriptor that effectively incorporates spatio-temporal information. Specifically, spatial attention within the same frame is utilized to learn spatial feature patterns, while attention in corresponding local regions of different frames is utilized to learn the persistence or change of features over time. We use a sliding window to control the temporal range of attention and use relative positional encoding to construct sequential relationships between different features. This allows our descriptors to capture the intrinsic dynamics in a sequence of frames.Comprehensive experiments on challenging benchmark datasets show that the proposed approach outperforms recent state-of-the-art methods.The code is available at https://github.com/tiev-tongji/Spatio-Temporal-SeqVPR.