The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Bayesian Loss for Crowd Count Estimation With Point Supervision
Open accessAbstract
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map estimation, which convert the sparse point annotations into a “ground truth” density map through a Gaussian kernel, and then use it as the learning target to train a density map estimator. However, such a "ground-truth" density map is imperfect due to occlusions, perspective effects, variations in object shapes, etc. On the contrary, we propose Bayesian loss, a novel loss function which constructs a density contribution probability model from the point annotations. Instead of constraining the value at every pixel in the density map, the proposed training loss adopts a more reliable supervision on the count expectation at each annotated point. Without bells and whistles, the loss function makes substantial improvements over the baseline loss on all tested datasets. Moreover, our proposed loss function equipped with a standard backbone network, without using any external detectors or multi-scale architectures, plays favourably against the state of the arts. Our method outperforms previous best approaches by a large margin on the latest and largest UCF-QNRF dataset.
Overview
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
Verification
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.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
Locality-constrained Linear Coding for image classification
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., & Gong, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540018 · Cited by 3,100 · cited 1×
“In overcrowded scenes, clutters and severe occlusions make it unfeasible to detect every single person, despite the progresses in related fields [19, 10, 47, 17, 33, 43, 61, 50, 48, 34, 49, 55, 60, 52].”
BackgroundSelf-citationSirinukunwattana, K., Raza, S. E. A., Tsang, Y.-W., Snead, D. R. J., Cree, I. A., & Rajpoot, N. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2525803 · Cited by 1,224
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network
Hsieh, M.-R., Lin, Y.-L., & Hsu, W. H. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.446 · Cited by 547
Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd
Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_39 · Cited by 488
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
Mundhenk, T. N., Konjevod, G., Sakla, W. A., & Boakye, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_48 · Cited by 386
Cited by
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
Wang, Q., Gao, J., Lin, W., & Li, X. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3013269 · Cited by 510
Few-Shot Class-Incremental Learning
Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., & Gong, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01220 · Cited by 499
Self-citationInfrared-Visible Cross-Modal Person Re-Identification with an X Modality
Li, D., Wei, X., Hong, X., & Gong, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5891 · Cited by 431
Self-citationAttention Scaling for Crowd Counting
Jiang, X., Zhang, L., Xu, M., Zhang, T., Lv, P., Zhou, B., Yang, X., & Pang, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00476 · Cited by 325
TransCrowd: weakly-supervised crowd counting with transformers
Liang, D., Chen, X., Xu, W., Zhou, Y., & Bai, X. (2022) · Science China Information Sciences · doi:10.1007/s11432-021-3445-y · Cited by 268
Metadata
- Authors
- Ma, Z., Wei, X., Hong, X., & Gong, Y.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 6141-6150
- OpenAlex
- W3004672782
- Cited by
- 617
- References
- 10
- FWCI
- 20.83
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Bayesian Loss for Crowd Count Estimation With Point Supervision. https://app.cochat.ai/papers/10.1109/iccv.2019.00624
- The paper
- Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019). Bayesian Loss for Crowd Count Estimation With Point Supervision. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv.2019.00624
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.