FastReID: A Pytorch Toolbox for General Instance Re-identification
Not on the map. Why?
Abstract (arXiv)
General Instance Re-identification is a very important task in the computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, and snapshop, etc.. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system in JD AI Research. In FastReID, highly modular and extensible design makes it easy for the researcher to achieve new research ideas. Friendly manageable system configuration and engineering deployment functions allow practitioners to quickly deploy models into productions. We have implemented some state-of-the-art projects, including person re-id, partial re-id, cross-domain re-id and vehicle re-id, and plan to release these pre-trained models on multiple benchmark datasets. FastReID is by far the most general and high-performance toolbox that supports single and multiple GPU servers, you can reproduce our project results very easily and are very welcome to use it, the code and models are available at https://github.com/JDAI-CV/fast-reid.
Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 25; 2022: 28; 2023: 22; 2024: 38; 2025: 35; 2026: 16.
164 papers.
Sort:
By area:
- 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
- 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
- 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
- 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 113
- 2022Exploring Dual-task Correlation for Pose Guided Person Image Generationcited by 68
- 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 63
- 2021Person Re-identification Method Based on Color Attack and Joint Defencecited by 56
- 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
- 2021Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Methodcited by 42
- 2022Deep Frequency Filtering for Domain Generalizationcited by 41
- 2022DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotationscited by 35
- 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
38 more
- 2021MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmarkcited by 28
- 2021Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identificationcited by 23
- 2021Explainable Person Re-Identification with Attribute-guided Metric Distillationcited by 23
- 2024Exploring Color Invariance through Image-Level Ensemble Learningcited by 23
- 2022Gait Recognition in the Wild with Multi-hop Temporal Switchcited by 22
- 2023TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenescited by 21
- 2024View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Networkcited by 21
- 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
- 2023Adaptive Sparse Pairwise Loss for Object Re-Identificationcited by 20
- 2023LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Predictioncited by 19
- 2024AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identificationcited by 19
- 2021Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptationcited by 18
- 2023Aerial-Ground Person Re-IDcited by 18
- 2021FlipReID: Closing the Gap between Training and Inference in Person Re-Identificationcited by 16
- 2022Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Spacecited by 16
- 2024BoostTrack++: using tracklet information to detect more objects in multiple object trackingcited by 15
- 2025SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networkscited by 15
- 2021Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identificationcited by 12
- 2022Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Citiescited by 12
- 2023Learning Feature Recovery Transformer for Occluded Person Re-identificationcited by 12
- 2025Omnidirectional Multi-Object Trackingcited by 12
- 2021Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identificationcited by 11
- 2021Learning to Disentangle Scenes for Person Re-identificationcited by 10
- 2022GEFF: Improving Any Clothes-Changing Person ReID Model using Gallery Enrichment with Face Featurescited by 10
- 2024Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Trainingcited by 10
- 2021Benchmarks for Corruption Invariant Person Re-identificationcited by 9
- 2023PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attackscited by 9
- 2024DeconfuseTrack:Dealing with Confusion for Multi-Object Trackingcited by 9
- 2024RelationVLM: Making Large Vision-Language Models Understand Visual Relationscited by 9
- 2024HOIST-Former: Hand-held Objects Identification, Segmentation, and Tracking in the Wildcited by 9
- 20212rd Place Solutions in the HC-STVG track of Person in Context Challenge 2021cited by 8
- 2021Semi-Supervised Domain Generalizable Person Re-Identificationcited by 8
- 2022PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identificationcited by 8
- 2022Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationcited by 8
- 2024Cross-video Identity Correlating for Person Re-identification Pre-trainingcited by 8
- 2025LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identificationcited by 8
- 2021TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognitioncited by 7
- 2021Learning Instance-level Spatial-Temporal Patterns for Person Re-identificationcited by 7
50 most cited of 164 All 164 (JSON)
- 2026FM-ReID: Selective Competitive Token Routing for Object Re-Identification29 Sep 2026
- 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT14 Sep 2026
- 2026A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification13 Sep 2026
- 2026YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification2 Sep 2026
- 2026VTO: Visual Tool Orchestration for Video Anomaly Detection8 Aug 2026
- 2026VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification3 Aug 2026
- 2026VLA-ReID: Video-Level Association for Re-Identification in Multi-Object Tracking with Highly Similar Objects19 Jul 2026
- 2026WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps9 Jul 2026
- 2026Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball28 May 2026
- 2026View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification18 May 2026
- 2026A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking15 May 2026
- 20263D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification29 Apr 2026
38 more
- 2026Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking6 Mar 2026
- 2026Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions6 Mar 2026
- 2026DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification1 Feb 2026
- 2026Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification29 Jan 2026
- 2025StableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections25 Nov 2025
- 2025Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration20 Nov 2025
- 2025Edge Assisted Multi-Camera Vehicle Tracking Framework for Real-Time and Scalable Deployment17 Nov 2025
- 2025ReIDMamba: Learning Discriminative Features with Visual State Space Model for Person Re-Identification11 Nov 2025
- 2025A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification7 Nov 2025
- 2025PCD-ReID: Occluded Person Re-Identification for Base Station Inspection3 Nov 2025
- 2025GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification25 Oct 2025
- 2025Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking10 Oct 2025
- 2025PCICF: A Pedestrian Crossing Identification and Classification Framework29 Sep 2025
- 2025NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking2 Sep 2025
- 2025BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT21 Aug 2025
- 2025CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification5 Aug 2025
- 2025LAVA: Language Driven Scalable and Versatile Traffic Video Analytics26 Jul 2025
- 2025RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking11 Jul 2025
- 2025When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking8 Jul 2025
- 2025SportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team Sports3 Jun 2025
- 2025Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking1 Jun 2025
- 2025S3CE-Net: Spike-guided Spatiotemporal Semantic Coupling and Expansion Network for Long Sequence Event Re-Identification30 May 2025
- 2025CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking2 May 2025
- 2025Person detection and re-identification in open-world settings of retail stores and public spaces1 May 2025
- 2025Visual Trajectory Prediction of Vessels for Inland Navigation1 May 2025
- 2025Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval16 Apr 2025
- 2025SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification13 Apr 2025
- 2025Deep LG-Track: An Enhanced Localization-Confidence-Guided Multi-Object Tracker2 Apr 2025
- 2025LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification31 Mar 2025
- 2025Multi-modal Multi-platform Person Re-Identification: Benchmark and Method21 Mar 2025
- 2025SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks10 Mar 2025
- 2025Omnidirectional Multi-Object Tracking6 Mar 2025
- 2025DashCop: Automated E-ticket Generation for Two-Wheeler Traffic Violations Using Dashcam Videos1 Mar 2025
- 2025Towards long-term player tracking with graph hierarchies and domain-specific features28 Feb 2025
- 2025CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification24 Feb 2025
- 2025CHIRLA: Comprehensive High-resolution Identification and Re-identification for Large-scale Analysis10 Feb 2025
- 2025YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID23 Jan 2025
- 2025PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues20 Jan 2025
50 newest of 164 All 164 (JSON)
- 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
- 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
- 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
- 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 113
- 2022Exploring Dual-task Correlation for Pose Guided Person Image Generationcited by 68
- 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 63
- 2021Person Re-identification Method Based on Color Attack and Joint Defencecited by 56
- 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
- 2021Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Methodcited by 42
- 2022Deep Frequency Filtering for Domain Generalizationcited by 41
- 2022DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotationscited by 35
- 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
12 most cited of 160 All 160 (JSON)
- 2026FM-ReID: Selective Competitive Token Routing for Object Re-Identification29 Sep 2026
- 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT14 Sep 2026
- 2026A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification13 Sep 2026
- 2026YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification2 Sep 2026
- 2026VTO: Visual Tool Orchestration for Video Anomaly Detection8 Aug 2026
- 2026VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification3 Aug 2026
- 2026VLA-ReID: Video-Level Association for Re-Identification in Multi-Object Tracking with Highly Similar Objects19 Jul 2026
- 2026WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps9 Jul 2026
- 2026Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball28 May 2026
- 2026View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification18 May 2026
- 2026A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking15 May 2026
- 20263D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification29 Apr 2026
12 newest of 160 All 160 (JSON)