CoChat

The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.

Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes

Jiang, Hangzhi, Zhang, Xin, Xiang, Shiming · 2024 · IEEE Transactions on Multimedia

Abstract

The detection performance in crowd scenes is limited by recalling hard objects (e.g., occluded objects). It requires that this kind of objects can be successfully detected and retained by the non-maximum suppression (NMS) while controlling false positives. The existing dynamic label assignment algorithms can help recall these objects by adaptively allocating appropriate positive samples, however, they ignore the alignment with the selecting rules of NMS. This leads to the fact that detecting objects in crowd scenes are still very sensitive to the NMS threshold setting. As a result, the existing methods can only set a low NMS threshold to avoid the excessive false positives, causing some objects failed to be recalled. And these methods also generally lack more excitation for positive samples, which hinders further facilitating the recall of hard instances in crowd scenes. This article proposes a novel dynamic label assignment strategy for object detection in crowd scenes, called non-maximum suppression guided label assignment (NGLA), which aligns the assignment strategy with NMS process and learns more prominent positive samples. Following NMS, NGLA introduces the IoU between samples with their corresponding best samples to define positive and negative samples. To cooperate with NGLA, an NMS-aware loss is proposed to dynamically assign sample weights when supervising sample predictions, which also considers the IoU with the best sample. In addition, for better classification p…

Overview

Integrity signals

Registry

Crossref · 10.1109/tmm.2023.3293333

Cites

51 of 51 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 51 references

Research works printed but not linked: 7

  1. Dai, 2016, R-FCN: Object detection via region-based fully convolutional networks, 379
  2. Zhang, 2019, Freeanchor: Learning to match anchors for visual object detection, 147
  3. Xu, 2020, R-CNN: Looking into pedestrian detection from another perspective, 19953
  4. Yang, 2018, Metaanchor: Learning to detect objects with customized anchors, 318
  5. Li, 2022, Estimating noise transition matrix with label correlations for noisy multi-label learning, 24184
  6. Sun, 2021, What makes for end-to-end object detection, 9934
  7. Liu, 2022, DAB-DETR: Dynamic anchor boxes are better queries for DETR

Cited by

Still being checked.

Metadata

Authors
Jiang, H., Zhang, X., & Xiang, S.
Affiliations
  • University of Chinese Academy of Sciences (CN)
  • Beijing Institute of Technology (CN)
Venue
IEEE Transactions on Multimedia
Published
2024
Volume
26
Pages
2207-2218
ISSN
  • 1520-9210 (ISSN-L)
  • 1941-0077
OpenAlex
W4383503678
Cited by
16
References
51
Citations by year
2026: 5 · 2025: 7 · 2024: 4
FWCI
1.45
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Multimedia (publishedVersion)
Funders
  • National Key Research and Development Program of China (2018AAA0100400)
  • National Natural Science Foundation of China (62076242)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
object detection, crowded scenes, non-maximum suppression, label assignment, occluded objects

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: Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes. https://app.cochat.ai/papers/10.1109/tmm.2023.3293333
The paper
Jiang, H., Zhang, X., & Xiang, S. (2024). Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2023.3293333

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.