The DOI matches its Crossref record; 65 of the 71 references it cites were found in a registry or an index.
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Abstract
We introduce a new dataset, Human3.6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models and algorithms. Besides increasing the size of the datasets in the current state-of-the-art by several orders of magnitude, we also aim to complement such datasets with a diverse set of motions and poses encountered as part of typical human activities (taking photos, talking on the phone, posing, greeting, eating, etc.), with additional synchronized image, human motion capture, and time of flight (depth) data, and with accurate 3D body scans of all the subject actors involved. We also provide controlled mixed reality evaluation scenarios where 3D human models are animated using motion capture and inserted using correct 3D geometry, in complex real environments, viewed with moving cameras, and under occlusion. Finally, we provide a set of large-scale statistical models and detailed evaluation baselines for the dataset illustrating its diversity and the scope for improvement by future work in the research community. Our experiments show that our best large-scale model can leverage our full training set to obtain a 20% improvement in performance compared to a training set of the scale of the largest existing public dataset for this problem. Yet the potential for improvement by leveraging higher capacity, more complex models with our large dataset, is substantially vaster and should stimulate future research. The dataset together with code for the associated large-scale learning models, features, visualization tools, as well as the evaluation server, is available online at http://vision.imar.ro/human3.6m.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Nonlinear Component Analysis as a Kernel Eigenvalue Problem
Schölkopf, B., Smola, A. J., & Müller, K. (1998) · Neural Computation · doi:10.1162/089976698300017467 · Cited by 8,196
Real-time human pose recognition in parts from single depth images
Shotton, J., Fitzgibbon, A. W., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., & Blake, A. (2011) · 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.2011.5995316 · Cited by 3,545
Multiple View Geometry in Computer Vision
(2001) · Kybernetes · doi:10.1108/k.2001.30.9_10.1333.2 · Cited by 3,376
Random Features for Large-Scale Kernel Machines
Rahimi, A., & Recht, B. (2007) · Cited by 2,783
Kernel methods in machine learning
Hofmann, T., Schölkopf, B., & Smola, A. J. (2008) · The Annals of Statistics · doi:10.1214/009053607000000677 · Cited by 2,292
SCAPE: shape completion and animation of people
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., & Davis, J. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073207 · Cited by 1,489
KERNEL METHODS IN MACHINE LEARNING
Hofmann, T., Schölkopf, B., & Smola, A. J. (2008) · Cited by 1,408
Sigal, L., Bălan, A. O., & Black, M. J. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0273-6 · Cited by 1,205
Poselets: Body part detectors trained using 3D human pose annotations
Bourdev, L., & Malik, J. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459303 · Cited by 961
Flagged first, then by citations
6 of the 71 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- 0, INRIA 4D
- 0, CMU HMC
- sminchisescu, 2011, Feature-based Human Pose Estimation in Guide to Visual Analysis of Humans Looking at People
Cited by
Sorted by citations
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
Dai, A., Chang, A. X., Savva, M., Halber, M., Funkhouser, T., & Niessner, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.261 · Cited by 4,368
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014) · 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.2014.471 · Cited by 2,699
“6M” [10] that includes images and 3D poses of people but are captured in the controlled indoor environments, whereas our dataset includes real-world images but provides 2D poses only.”
BackgroundSUN RGB-D: A RGB-D scene understanding benchmark suite
Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943
“There are many existing RGB-D datasets available [54] [47] [1] [25] [44] [60] [49] [45] [29] [66] [57] [52] [46] [16] [21] [73] [35] [67] [3] [41] [10] [63] [42] [64] [65] [48] [12] [33] [8] [50] [26] [6].”
End-to-End Recovery of Human Shape and Pose
Kanazawa, A., Black, M. J., Jacobs, D. W., & Malik, J. (2018) · 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.2018.00744 · Cited by 1,962
Metadata
- Authors
- Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C.
- Affiliations
- IMAR - Institutul de Matematică „Simion Stoilow” al Academiei Române (RO)
- Lund University (SE)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2014-07
- Volume
- 36
- Issue
- 7
- Pages
- 1325-1339
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2101032778
- Cited by
- 3,653
- References
- 71
- Citations by year
- 2026: 349 · 2025: 529 · 2024: 581 · 2023: 543 · 2022: 390 · 2021: 429 · 2020: 305 · 2019: 235 · 2018: 133 · 2017: 78 · 2016: 48 · 2015: 20 · 2014: 10
- FWCI
- 46.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Lund University Publications (Lund University) (submittedVersion)
- Funders
- Universitatea Politehnica din București
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Keywords
- 3D human pose estimation, natural environment, 3D body scans, occlusion, human activities
- MeSH terms
- Algorithms, Biometry, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Pattern Recognition, Automated, Photography, Posture, Sensitivity and Specificity, Subtraction Technique, Reproducibility of Results, Databases, Factual, Information Storage and Retrieval, Ecosystem, Imaging, Three-Dimensional, Whole Body Imaging
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
