Person re-identification (Market-1501, DukeMTMC, MSMT17)
← Most-used data · All Face, person and video benchmarks datasets
Faces, people, poses, facial expressions and human actions in images and video.
Tasks, access and usage conditions#
Mention counts below measure name matches in tracked papers, not benchmark quality or downloads. A family count can cover multiple datasets; it is not a separate count for each comparison row. Choose a task and version first, preserve evaluation splits, and follow the linked release terms. The site's content license does not replace the datasets' own terms.
| Dataset / version | Task and evaluation | Access and preparation | Usage conditions |
|---|---|---|---|
| Market-1501 | Cross-camera person retrieval; 32,668 bounding boxes of 1,501 identities. Evaluation: Report mAP and CMC/rank-1 with the official exclusions; disclose single-/multi-query and re-ranking. | Official source / documentation Use the authors’ release links and preserve train, query, gallery, junk and distractor conventions. | The source requests citation. It does not establish a blanket commercial reuse license here; confirm permission and source-image conditions. |
| DukeMTMC / DukeMTMC-reID — historical benchmark | Multi-camera tracking and a derived person-reidentification benchmark. Evaluation: Identify parent versus re-ID derivative when reading older results; choose a currently authorized dataset for a new study. | Official source / documentation The linked dataset-lifecycle study documents retraction of the parent dataset. No active authorized download is recommended here. | Retraction and continued availability of third-party copies are different things. Do not infer authorization from a mirror. |
| MSMT17 | Person re-identification across cameras and recording conditions. Evaluation: Preserve the release’s identity-disjoint split; report mAP/rank-1, camera setup and version. | Official source / documentation The release agreement specifies case-by-case academic access from PKU. Confirm present availability with the owner; the agreement itself is not a download. | Academic, non-commercial scientific research; signed agreement, required citation and restrictions on redistribution and publishing images. |
Key findings#
- From Nov 2023 to Oct 2026, 42 archived papers mentioned Person re-identification (Market-1501, DukeMTMC, MSMT17) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Dec 2023 (5).
- Person re-identification (Market-1501, DukeMTMC, MSMT17) was mentioned in 2 papers in the last 30 days (2026-10-07 to 2026-11-05), ranking #127 of the 246 datasets mentioned.
- By journal category: AI (2).
- Most of them appeared in Artificial Intelligence Review (1) and Pattern Recognition (1).
- From 2017 to 2026 (so far), Person re-identification (Market-1501, DukeMTMC, MSMT17) was mentioned in 82 papers in the tracked journals, most of them in AI (82).
- 12 of them were published in 2025, against 0 in 2017.
- Since 2023, the institutions with the most of these papers were Peking University (6), Chinese Academy of Sciences (5) and University of Chinese Academy of Sciences (5).
- The journals publishing most of them were IEEE Transactions on Pattern Analysis and Machine Intelligence (11), International Journal of Computer Vision (8) and Pattern Recognition (5).
- The most-cited of them is “Improving person re-identification by attribute and identity learning” (Pattern Recognition, 2019), with 864 citations.
- Papers use Person re-identification (Market-1501, DukeMTMC, MSMT17) most often with ImageNet (21), MS COCO (6) and CIFAR-10 / CIFAR-100 (3); it has 4 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.
Mentions over 36 months#
| Trend | Nov 23–Oct 24 | Nov 24–Oct 25 | Nov 25–Oct 26 | 36 months |
|---|---|---|---|---|
| 21 | 14 | 7 | 42 |
Papers per year#
20172026 (so far)
| Category | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 (so far) |
|---|---|---|---|---|---|---|---|---|---|---|
| AI | 0 | 2 | 6 | 5 | 15 | 6 | 13 | 17 | 12 | 6 |
| All categories | 0 | 2 | 6 | 5 | 15 | 6 | 13 | 17 | 12 | 6 |
Where the papers come from#
| # | Journal | Papers |
|---|---|---|
| 1 | IEEE Transactions on Pattern Analysis and Machine Intelligence | 11 |
| 2 | International Journal of Computer Vision | 8 |
| 3 | Pattern Recognition | 5 |
| 4 | IEEE Transactions on Neural Networks and Learning Systems | 5 |
| 5 | Artificial Intelligence Review | 3 |
| 6 | Machine Learning | 3 |
| 7 | Expert Systems with Applications | 3 |
| 8 | Neural Computing and Applications | 2 |
| 9 | Knowledge-Based Systems | 2 |
| 10 | Information Fusion | 2 |
| # | Institution | Papers |
|---|---|---|
| 1 | Peking University | 6 |
| 2 | Chinese Academy of Sciences | 5 |
| 3 | University of Chinese Academy of Sciences | 5 |
| 4 | Peng Cheng Laboratory | 4 |
| 5 | University of Trento | 3 |
| 6 | Zhejiang University | 3 |
| 7 | Beijing Jiaotong University | 2 |
| 8 | Changchun Normal University | 2 |
| 9 | Chongqing University of Posts and Telecommunications | 2 |
| 10 | Fudan University | 2 |
| # | Country | Papers |
|---|---|---|
| 1 | China | 36 |
| 2 | United States | 12 |
| 3 | United Kingdom | 4 |
| 4 | Italy | 4 |
| 5 | Australia | 3 |
| 6 | Sweden | 3 |
| 7 | Hong Kong | 2 |
| 8 | South Korea | 2 |
| 9 | Switzerland | 1 |
| 10 | Spain | 1 |
| # | Keyword | Papers |
|---|---|---|
| 1 | person re-identification | 25 |
| 2 | Market-1501 | 6 |
| 3 | knowledge distillation | 5 |
| 4 | multimodal fusion | 4 |
| 5 | unsupervised domain adaptation | 4 |
| 6 | attention mechanism | 3 |
| 7 | benchmark dataset | 3 |
| 8 | data augmentation | 3 |
| 9 | distribution shift | 3 |
| 10 | domain generalization | 3 |
Most-cited papers#
| # | Citations | Per month | Title | Journal | Published | Authors |
|---|---|---|---|---|---|---|
| 1 | 864 | 9.7 | Improving person re-identification by attribute and identity learning | Pattern Recognition | 2019-06-06 | Yutian Lin, Liang Zheng, Zhedong Zheng et al. |
| 2 | 248 | 2.4 | A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2018-02-19 | Srikrishna Karanam, Mengran Gou, Ziyan Wu et al. |
| 3 | 227 | 2.5 | AlignedReID++: Dynamically matching local information for person re-identification | Pattern Recognition | 2019-05-15 | Hao Luo, Wei Jiang, Xuan Zhang et al. |
| 4 | 147 | 2.2 | Identifying Visible Parts via Pose Estimation for Occluded Person Re-Identification | IEEE Transactions on Neural Networks and Learning Systems | 2021-03-02 | Jiaxu Miao, Yu Wu, Yi Yang |
| 5 | 142 | 3.9 | Occluded person re-identification with deep learning: A survey and perspectives | Expert Systems with Applications | 2023-11-02 | Enhao Ning, Changshuo Wang, Huang Zhang et al. |
Used together with#
| Used with | Type | Papers using both | Lift |
|---|---|---|---|
| ImageNet | Dataset | 21 | 5.2 |
| MS COCO | Dataset | 6 | 3.8 |
| CIFAR-10 / CIFAR-100 | Dataset | 3 | 1.3 |
| Face recognition (LFW, CelebA, VGGFace2) | Dataset | 3 | 5.9 |
| Date | Title | Journal | Authors | Affiliations |
|---|---|---|---|---|
| 2026-10-22 | Beyond the survey: a systematic empirical study of detection and association in visual MOT | Artificial Intelligence Review | Linh Van Ma, Juhua Hu, Wei Cheng et al. | Gwangju Institute of Science and Technology; University of Washington Tacoma |
| 2026-10-07 | Koopman Re-ID: Modeling invariant and variant features for person re-identification | Pattern Recognition | Jinlong Zhu, Wendong Sun, Qingliang Li et al. | Changchun Normal University |
Cite this page
Scholar4AI. (2026). Person re-identification (Market-1501, DukeMTMC, MSMT17). Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/person-re-identification-market-1501-dukemtmc-msmt17
@misc{scholar4ai-datasets-person-re-identification-market-1501-dukemtmc-msmt17,
author = {{Scholar4AI}},
title = {Person re-identification (Market-1501, DukeMTMC, MSMT17)},
year = {2026},
howpublished = {\url{https://scholar4ai.com/datasets/person-re-identification-market-1501-dukemtmc-msmt17}},
urldate = {2026-11-05},
note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}