Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
Open accessAbstract
Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In addition, the lack of pixel-level correspondence supervision in the VPR dataset hinders further improvement of the local feature matching capability in the re-ranking stage. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
V-LOAM integrated visual odometry with LiDAR-based mapping, leveraging complementary geometric and texture features.
“Early multimodal fusion approaches, such as V-LOAM [143], integrated visual odometry with LiDAR-based mapping, effectively leveraging the complementary nature of geometric and texture-based features.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [143]
The Related Works and Two-Stage VPR sections discuss image-based visual place recognition, not V-LOAM. Searches for V-LOAM, LiDAR-based mapping, and visual odometry found no passage in our copy addressing the attributed integration or its geometric and texture features. The returned passages have no page numbers. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · cited 1× · see citing works
“One-Stage VPR: The one-stage VPR approaches produce global representations for image matching by aggregating early handcrafted local features (Bay, Tuytelaars, and Van Gool 2006) or deep learning-based features from convolutional neural networks (Arandjelovic et al. 2016), MLPs (Ali-bey,…”
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Arandjelović, R., Gronát, P., Torii, A., Pajdla, T., & Šivic, J. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.572 · Cited by 3,441 · cited 8× · see citing works
“Mean-while, SALAD (Izquierdo and Civera 2024) redefines NetVLAD (Arandjelovic et al. 2016)’s soft-assignment as the optimal transmission problem aggregating local features from DINOv2.”
InfluentialIn Defense of the Triplet Loss for Person Re-IdentificationPreprint
Hermans, A., Beyer, L., & Leibe, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.07737 · Cited by 3,271 · cited 1× · see citing works
“Similarly, we can get the background prototype f bg : Next, Based on triplet loss (Hermans, Beyer, and Leibe 2017) L CE can be defined as: where f p fg is the foreground prototype of the positive sample (different images of the same scene), as shown in Figure 2.”
Datta, R., Joshi, D., Li, J., & Wang, J. Z. (2008) · ACM Computing Surveys · doi:10.1145/1348246.1348248 · Cited by 3,043 · cited 1× · see citing works
“Early approaches viewed VPR as a single-stage image retrieval problem (Datta et al. 2008), using global features ( a.k.a. global descriptors) to represent the location image, similarity search in that feature space, and determining the localized location by nearest neighbor matching.”
DINOv2: Learning Robust Visual Features without Supervision
Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.07193 · Cited by 1,078 · cited 7× · see citing works
“Feature Extractor: Following prior works (Keetha et al. 2023; Lu et al. 2024d; Izquierdo and Civera 2024; Lu et al. 2024b), we adopt the pre-trained DINOv2 model (Oquab et al. 2023) as the feature extractor for our visual place recognition (VPR) pipeline.”
InfluentialMulti-Similarity Loss With General Pair Weighting for Deep Metric Learning
Wang, X., Han, X., Huang, W., Dong, D., & Scott, M. R. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00516 · Cited by 893 · cited 2× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
Hausler, S., Garg, S., Xu, M., Milford, M. J., & Fischer, T. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01392 · Cited by 461 · cited 4× · see citing works
“Additionally, we compare our method with three two-stage methods that incorporate re-ranking: Patch-NetVLAD (Hausler et al. 2021), R2Former (Zhu et al. 2023), and SelaVPR (Lu et al. 2024d).”
InfluentialMapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition
Warburg, F., Hauberg, S., López-Antequera, M., Gargallo, P., Kuang, Y., & Civera, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00270 · Cited by 235 · cited 13× · see citing works
“Specifically, FoL-re-ranking improves the absolute R@1 by 1.3%, 1.3%, 5.0%, and 3.8% on Pitts250k-test, MSLS-val, MSLS-challenge, and Tokyo24/7, respectively.”
InfluentialFAB-MAP + RatSLAM: Appearance-based SLAM for multiple times of day
Glover, A., Maddern, W., Milford, M. J., & Wyeth, G. F. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509547 · Cited by 216 · cited 1× · see citing works
“St. Lucia (Glover et al. 2010).”
Scalable 6-DOF Localization on Mobile Devices
Middelberg, S., Sattler, T., Untzelmann, O., & Kobbelt, L. P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10605-2_18 · Cited by 198 · cited 1× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
TransVPR: Transformer-Based Place Recognition with Multi-Level Attention Aggregation
Wang, R., Shen, Y., Zuo, W., Zhou, S., & Zheng, N. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01328 · Cited by 190 · cited 1× · see citing works
“TransVPR (Wang et al. 2022b) leverages the transformer ar-chitecture’s multi-level attention mechanism to derive global features for candidate retrieval, and uses an attention mask to filter the feature map to generate key patch descriptors for reordering candidates.”
Self-supervising Fine-Grained Region Similarities for Large-Scale Image Localization
Ge, Y., Wang, H., Zhu, F., Zhao, R., & Li, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58548-8_22 · Cited by 175 · cited 2× · see citing works
“In this section, we compare our one-stage (FoL-global) and two-stage (FoL-re-ranking) results with previous state-of-the-art VPR methods, including eight one-stage meth-ods that utilize global feature retrieval: NetVLAD (Arand-jelovic et al. 2016), SFRS (Ge et al. 2020), CosPlace (Berton, Masone, and Caputo 2022b), Mi…”
Only look once, mining distinctive landmarks from ConvNet for visual place recognition
Chen, Z., Maffra, F., Sa, I., & Chli, M. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202131 · Cited by 153 · cited 1× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
Zaffar, M., Garg, S., Milford, M. J., Kooij, J. F. P., Flynn, D., McDonald-Maier, K. D., & Ehsan, S. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01469-5 · Cited by 150 · see citing works
Visual Place Recognition with Repetitive Structures
Torii, A., Šivic, J., Okutomi, M., & Pajdla, T. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2409868 · Cited by 136 · cited 2× · see citing works
“Pitts250k (Torii et al. 2013) consists of images from Google Street View panoramas, exhibiting significant viewpoint changes, moderate condition variations, and a small number of dynamic objects.”
24/7 Place Recognition by View Synthesis
Torii, A., Arandjelović, R., Šivic, J., Okutomi, M., & Pajdla, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2667665 · Cited by 111 · cited 2× · see citing works
“Tokyo24/7 (Torii et al. 2015) includes approximately 76,000 database images and 315 query images from urban environments, each image involving three different viewpoints and three different times of the day, showcasing significant changes in lighting conditions.”
BoQ: A Place is Worth a Bag of Learnable Queries
Ali-bey, A., Chaib-draa, B., & Giguère, P. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01685 · Cited by 44 · see citing works
CNDesc: Cross Normalization for Local Descriptors Learning
Wang, C., Xu, R., Xu, S., Meng, W., & Zhang, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3169331 · Cited by 42 · see citing works
Self-citationAmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift
Yildiz, B., Khademi, S., Siebes, R., & van Gemert, J. C. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956049 · Cited by 27 · cited 2× · see citing works
“AmsterTime (Yildiz et al. 2022) is a challenging dataset of 1,231 image pairs from Amsterdam, each containing a historical grayscale query and a contemporary RGB reference of the same location.”
Learning local shape descriptors for computing non-rigid dense correspondence
Guo, J., Wang, H., Cheng, Z., et al. (2020) · Computational Visual Media · doi:10.1007/s41095-020-0163-y · Cited by 20 · cited 1× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures
Wang, Y., Guo, J., Dong-ming Yan, A., Wang, K., & Zhang, X. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00639 · Cited by 19 · cited 2× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
Adaptive-Attentive Geolocalization From Few Queries: A Hybrid Approach
Paolicelli, V., Berton, G., Montagna, F., Masone, C., & Barbara Caputo, B. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.841817 · Cited by 16 · cited 6× · see citing works
“Specifically, these datasets include Pitts30k , Eynsham , SVOX Rain , and St. Lucia .”
InfluentialSegment Anything Model Is a Good Teacher for Local Feature Learning
Wu, J., Xu, R., Wood-Doughty, Z., Wang, C., Xu, S., & Lam, E. Y. M. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3554033 · Cited by 16 · cited 1× · see citing works
“Second, we introduce a weakly supervised local feature training strategy to improve the performance of local matching (Xu et al. 2024; Wu et al. 2023) in the re-ranking stage.”
Self-citationTowards Seamless Adaptation of Pre-trained Models for Visual Place RecognitionPreprint
Lu, F., Zhang, L., Lan, X., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.14505 · Cited by 10 · see citing works
Self-supervised discriminative model prediction for visual tracking
Yuan, D., Geng, G., Shu, X., Liu, Q., Chang, X., He, Z., & Shi, G. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09348-5 · Cited by 6 · cited 1× · see citing works
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
Mutually-Guided Hierarchical Multi-Modal Feature Learning for Referring Image Segmentation
Li, J., Xie, Q., Chang, X., et al. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3698771 · cited 1×
“…the most similar locations from geo-tagged databases to estimate the rough geographic loca-a tion of a query image and is an essential part of many robotics (Chen et al. 2017) and computer vision (Middelberg et al. 2014; Wang et al. 2019b; Guo et al. 2020; Yuan et al. 2024; Li et al. 2024) tasks.”
AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain ShiftPreprint
Yildiz, B. C., Khademi, S., Siebes, R., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.16291
Flagged first, then by citations
Research works printed but not linked: 14
- Ali-bey, A.; Chaib-draa, B.; and Giguère, P. 2023. MixVPR: Feature Mixing for Visual Place Recognition. In WACV, 2998-3007.
- Berton, G.; Masone, C.; and Caputo, B. 2022a. Rethinking visual geo-localization for large-scale applications. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4878-4888.
- Berton, G.; Masone, C.; and Caputo, B. 2022b. Rethink- ing visual geo-localization for large-scale applications. In CVPR, 4878-4888.
- Berton, G.; Trivigno, G.; Caputo, B.; and Masone, C. 2023. EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition. In Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision (ICCV), 11080- 11090.
- Cuturi, M. 2013. Sinkhorn distances: Lightspeed computa- tion of optimal transport. Advances in neural information processing systems, 26.
- Izquierdo, S.; and Civera, J. 2024. Optimal Transport Aggre- gation for Visual Place Recognition. In Accepted to CVPR.
- Keetha, N.; Mishra, A.; Karhade, J.; Jatavallabhula, K. M.; Scherer, S.; Krishna, M.; and Garg, S. 2023. Anyloc: To- wards universal visual place recognition. IEEE Robotics and Automation Letters.
- Lu, F.; Dong, S.; Zhang, L.; Liu, B.; Lan, X.; Jiang, D.; and Yuan, C. 2024a. Deep Homography Estimation for Visual Place Recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, 10341-10349.
- Lu, F.; Lan, X.; Zhang, L.; Jiang, D.; Wang, Y.; and Yuan, C. 2024b. CricaVPR: Cross-image Correlation-aware Rep- resentation Learning for Visual Place Recognition. In Ac- cepted to CVPR.
- Lu, F.; Zhang, L.; Lan, X.; Dong, S.; Wang, Y.; and Yuan, C. 2024d. Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition. In ICLR.
- Sünderhauf, N.; Neubert, P.; and Protzel, P. 2013. Are we there yet? Challenging SeqSLAM on a 3000 km journey across all four seasons. In Workshop on Long-Term Auton- omy, IEEE International Conference on Robotics and Au- tomation (ICRA).
- Van Erven, T.; and Harremos, P. 2014. Rényi divergence and Kullback-Leibler divergence. IEEE Transactions on Infor- mation Theory, 60(7): 3797-3820.
- Wang, C.; Xu, R.; Lu, K.; Xu, S.; Meng, W.; Zhang, Y.; Fan, B.; and Zhang, X. 2023. Attention weighted local descrip- tors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9): 10632-10649.
- Zhu, S.; Yang, L.; Chen, C.; Shah, M.; Shen, X.; and Wang, H. 2023. R 2 Former: Unified retrieval and reranking trans- former for place recognition. In CVPR, 19370-19380.
Cited by
Sorted by citations
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“This highlights the value of merging data-driven and model-based methods for reliable localization [141, 142].”
Self-citation3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering
Xu, R., Gao, H., Yu, M., An, D. U., Chen, S., Wang, C., Guo, L., Liang, X., & Xu, S. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247159 · Cited by 1 · see citing works
Self-citationWang, L., Lan, C., Wu, B., Yao, F., Wei, Z., Gao, T., & Yu, H. W. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115285 · Cited by 1 · see citing works
Multi-view adversarial domain adaptation for visual place recognition
Wang, Y., Chi, H., Geng, H., et al. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00499-8 · Cited by 1 · see citing works
Enhancing Quantization for Visual Autoregressive Generation Via Uncertainty Identification
Liu, J., Xiong, G., Ren, S., Gao, R., Yu, L., & Fu, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462147 · Cited by 1 · see citing works
Self-citationVehicle-Scene Interaction: A Text-Driven 3-D Lidar Place Recognition Method for Autonomous Driving
Shang, T., Li, Z., Xu, P., et al. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3676077
“Conventional visual place recognition (VPR) methods [1], [2], [3], [4], [5], [6] primarily use monocular imaging to establish location correspondences.”
Task-Aware Geometric Embeddings and Cross-Modal Interaction for 3D VQA
Gao, H., Xu, R., Wang, C., Guo, L., & Xu, S. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477363
“Seminal datasets like ScanQA [1] have established benchmarks, while transformer-based architectures better model complex spatial and semantic relationships [7, 17, 18].”
Self-citationUAFD: Unified Adaptive Frequency-Domain Detector for Generalizable Deepfake Detection
Zhou, J., Ma, H., Wang, W., Ren, S., & Fu, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462533
Self-citation3GeM Pooling: Direction-aware and Compact Global Descriptors for Visual Place Recognition
Zhang, X., Lu, F., Ye, C., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461747
DSPFusion: Depth and Semantic Prior Guided Multi-Focus Image Fusion with Vision Foundation Models
Wei, X., Huang, W., Hu, K., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465015
Self-citationHybrid State Space Modeling for Sequence-Based Robot Localization Under Challenging Environments
Li, Z., & Shang, T. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3714880
Deep Learning for Ship Re-identification: A Survey and Outlook
He, Y., Lin, G., Lu, W., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0291-1_31
GraphSeqLoc: Image Sequence-based Place recognition via Scene Graphs and Temporal Re-rankingPreprint
Pinkin, E., Kartashov, G., Kalmykov, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7422535
Ding, X., Jiao, N., Chi, Y., et al. (2026) · Displays · doi:10.1016/j.displa.2026.103708
- Authors
- Wang, C., Chen, S., Song, Y., Xu, R., Zhang, Z., Zhang, J., Yang, H., Zhang, Y., Fu, K., Du, S., Xu, Z., Gao, L., Guo, L., & Xu, S.
- Affiliations
- Qilu University of Technology (CN)
- Beijing University of Posts and Telecommunications (CN)
- Chinese Academy of Sciences (CN)
- Tongji University (CN)
- Fuzhou University (CN)
- Shandong University (CN)
- ORCID
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2025-04-11
- Volume
- 39
- Issue
- 7
- Pages
- 7536-7544
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W4409366443
- Cited by
- 17
- References
- 25
- Citations by year
- 2026: 13 · 2025: 4
- FWCI
- 12.69
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Figshare (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62162044, 32271983, 62171321, 62271074)
- Beihang University (VRLAB2023B01)
- Natural Science Foundation of Shandong Province (2023HWYQ)
- State Key Laboratory of Virtual Reality Technology and Systems (VRLAB2023B01)
- National Science and Technology Major Project (2022ZD0116800)
- Young Scientists Fund
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- visual place recognition, re-ranking, perceptual aliasing, two-stage retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
