# MMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments

arXiv: https://arxiv.org/abs/2505.12254 · HTML: https://mlsanity.com/paper/2505.12254/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 69 references that are in the map.
- First posted on arXiv 18 May 2025.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [BoQ: A Place is Worth a Bag of Learnable Queries](https://mlsanity.com/paper/2405.07364/) (2024)
- [Night-to-Day Image Translation for Retrieval-based Localization](https://mlsanity.com/paper/1809.09767/) (2018)
- [Viewpoint Invariant Dense Matching for Visual Geolocalization](https://mlsanity.com/paper/2109.09827/) (2021)
- [AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift](https://mlsanity.com/paper/2203.16291/) (2022)
- [Large-scale Localization Datasets in Crowded Indoor Spaces](https://mlsanity.com/paper/2105.08941/) (2021)
- [CV-Cities: Advancing Cross-View Geo-Localization in Global Cities](https://mlsanity.com/paper/2411.12431/) (2024)
- [VBR: A Vision Benchmark in Rome](https://mlsanity.com/paper/2404.11322/) (2024)
- [Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition](https://mlsanity.com/paper/2504.09881/) (2025)
- [NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences](https://mlsanity.com/paper/2110.09004/) (2021)
- [Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation](https://mlsanity.com/paper/1907.11004/) (2019)
- [MeshVPR: Citywide Visual Place Recognition Using 3D Meshes](https://mlsanity.com/paper/2406.02776/) (2024)
- [HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images](https://mlsanity.com/paper/2212.14649/) (2022)
- [DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing](https://mlsanity.com/paper/2311.00230/) (2023)

## Built on by (most cited first, 3 of 3)

- [SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition](https://mlsanity.com/paper/2509.25723/) (2025)
- [Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception](https://mlsanity.com/paper/2605.09936/) (2026)
- [AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition](https://mlsanity.com/paper/2609.04369/) (2026)

## Abstract (arXiv)

Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underrepresent dense pedestrian street scenes, particularly in non-Western urban contexts. We present MMS-VPR, a challenging fine-grained multimodal benchmark for pedestrian-level place recognition in dense urban environments. MMS-VPR comprises 110,529 images and 2,527 video clips across 208 fine-grained location classes within a ~70,800 m2 urban district in Chengdu, China, with adjacent classes separated by as little as 10-20 m. Unlike large-area VPR datasets, MMS-VPR elevates difficulty through visual ambiguity: repetitive storefronts, dense occlusion, and rapid viewpoint changes. Field data were collected in 2024 following a systematic multi-direction, dual-perspective protocol; social media imagery spans seven years (2019-2025), providing long-term appearance change across 31,726 geolocated photographs. Each location features day-night coverage, multiple viewing angles, and multimodal annotations including GPS coordinates, timestamps, semantic text, and an explicit spatial graph with space syntax enrichments. We release MMS-VPRlib, a unified benchmarking platform consolidating 22 baselines spanning shallow ML, CNN, Transformer, graph neural network (GNN), and multimodal architectures under a standardized, reproducible pipeline. Controlled modality ablations show that video temporal features are the most powerful single modality (+15.8% accuracy over image-only), semantic text provides superior coarse retrieval (R@5 = 0.988 alone), and full multimodal fusion achieves 0.981 accuracy, a +19.2% gain over image-only, while graph-structured modeling provides additional signal in fine-grained structural subsets. The dataset is available at https://huggingface.co/datasets/Yiwei-Ou/MMS-VPR and the benchmark at https://github.com/yiasun/MMS-VPRlib.