# DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition

arXiv: https://arxiv.org/abs/2011.08518 · HTML: https://mlsanity.com/paper/2011.08518/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

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

- [Sequence-Based Filtering for Visual Route-Based Navigation: Analysing the Benefits, Trade-offs and Design Choices](https://mlsanity.com/paper/2103.01994/) (2021)
- [Data-Efficient Sequence-Based Visual Place Recognition with Highly Compressed JPEG Images](https://mlsanity.com/paper/2302.13314/) (2023)
- [Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition](https://mlsanity.com/paper/2103.02074/) (2021)
- [SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition](https://mlsanity.com/paper/2106.11481/) (2021)
- [Text2Graph VPR: A Text-to-Graph Expert System for Explainable Place Recognition in Changing Environments](https://mlsanity.com/paper/2512.18613/) (2025)

## Abstract (arXiv)

Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions. These systems, however, rely on complex handcrafted heuristics for sequential matching - which are applied on top of a pre-computed pairwise similarity matrix between reference and query image sequences of a single route - to further reduce false-positive rates compared to single-frame retrieval methods. As a result, performing multi-frame place recognition can be extremely slow for deployment on autonomous vehicles or evaluation on large datasets, and fail when using relatively short parameter values such as a sequence length of 2 frames. In this paper, we propose DeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual and positional representations from a single monocular image sequence of a route. We demonstrate our approach on two large benchmark datasets, Nordland and Oxford RobotCar - recorded over 728 km and 10 km routes, respectively, each during 1 year with multiple seasons, weather, and lighting conditions. On Nordland, we compare our method to two state-of-the-art sequence-based methods across the entire route under summer-winter changes using a sequence length of 2 and show that our approach can get over 72% AUC compared to 27% AUC for Delta Descriptors and 2% AUC for SeqSLAM; while drastically reducing the deployment time from around 1 hour to 1 minute against both. The framework code and video are available at https://mchancan.github.io/deepseqslam