Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,955

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Fast Feature Pyramids for Object Detection

Dollar, Piotr, Appel, Ron, Belongie, Serge, Perona, Pietro·2014·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2014.2300479
Open this paper in CoChat — free account

Abstract

Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finely-sampled image pyramid. Our key insight is that one may compute finely sampled feature pyramids at a fraction of the cost, without sacrificing performance: for a broad family of features we find that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid. Extrapolation is inexpensive as compared to direct feature computation. As a result, our approximation yields considerable speedups with negligible loss in detection accuracy. We modify three diverse visual recognition systems to use fast feature pyramids and show results on both pedestrian detection (measured on the Caltech, INRIA, TUD-Brussels and ETH data sets) and general object detection (measured on the PASCAL VOC). The approach is general and is widely applicable to vision algorithms requiring fine-grained multi-scale analysis. Our approximation is valid for images with broad spectra (most natural images) and fails for images with narrow band-pass spectra (e.g., periodic textures).

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2014.2300479

Cites

13 of 13 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 13 references

Research works printed but not linked: 63

  1. 10.1109/ICCV.2009.5459207 · DOI · Paper page
  2. maji, 2008, Classification Using Intersection Kernel SVMs Is Efficient, Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR)
  3. lin, 2008, A Pose-Invariant Descriptor for Human Detection and Segmentation, Proc 10th European Conf Computer Vision (ECCV)
  4. 10.1109/CVPR.2007.383134 · DOI · Paper page
  5. 10.1109/CVPR.2010.5540102 · DOI · Paper page
  6. park, 2010, Multiresolution Models for Object Detection, Proc 11th European Conf Computer Vision (ECCV)
  7. wojek, 2008, A Performance Evaluation of Single and Multi-Feature People Detection, Proc 30th DAGM Symp Pattern Recognition (DAGM)
  8. 10.5244/C.24.68 · DOI · Paper page
  9. 10.1109/ICCV.2009.5459205 · DOI · Paper page
  10. 10.1103/PhysRevLett.73.814 · DOI · Paper page
  11. 10.1109/TPAMI.2011.155 · DOI · Paper page
  12. 10.1109/CVPR.2012.6248017 · DOI · Paper page
  13. 10.1109/ICCV.2007.4409092 · DOI · Paper page
  14. 10.1016/0042-6989(78)90232-8 · DOI · Paper page
  15. wojek, 2008, Sliding-Windows for Rapid Object Class Localization: A Parallel Technique, Proc 30th DAGM Symp Pattern Recognition
  16. 10.1109/IVS.2010.5548145 · DOI
  17. zhang, 2008, Efficient Scan-Window Based Object Detection Using GPGPU, Proc Workshop Visual Computer Vision on GPU?s (CVGPU)
  18. zhu, 2006, Fast Human Detection Using a Cascade of Histograms of Oriented Gradients, Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR)
  19. 10.1007/s11263-005-6644-8 · DOI · Paper page
  20. 10.1109/CVPR.2005.188 · DOI · Paper page
  21. 10.1109/CVPR.2001.990517 · DOI · Paper page
  22. 10.1109/TPAMI.2009.109 · DOI · Paper page
  23. 10.1177/0278364909341884 · DOI
  24. 10.5244/C.23.91 · DOI · Paper page
  25. 10.1088/0954-898X/5/4/006 · DOI · Paper page
  26. 10.2307/2310428 · doi:10.2307/2310428
  27. 10.1007/BF00288907 · DOI · Paper page
  28. 10.1113/jphysiol.1968.sp008455 · DOI · Paper page
  29. 10.1016/0042-6989(82)90113-4 · DOI · Paper page
  30. 10.1109/ICCV.2007.4408860 · DOI
  31. 10.1023/A:1011113216584 · DOI · Paper page
  32. 10.1109/CVPR.2010.5540226 · DOI · Paper page
  33. gu, 2009, Recognition Using Regions, Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR)
  34. 10.1007/s11263-007-0095-3 · DOI · Paper page
  35. 10.1109/CVPR.2003.1211479 · DOI · Paper page
  36. agarwal, 2002, Learning a Sparse Representation for Object Detection, Proc European Conf Computer Vision (ECCV)
  37. weber, 2000, Unsupervised Learning of Models for Recognition, Proc European Conf Computer Vision (ECCV)
  38. 10.1109/CVPR.2000.854739 · DOI · Paper page
  39. 10.1109/TASSP.1987.1165137 · DOI · Paper page
  40. 10.1109/ICIP.1996.559512 · DOI · Paper page
  41. doll�r, 2012, Crosstalk Cascades for Frame-Rate Pedestrian Detection, Proc 12th European Conf Computer Vision (ECCV)
  42. 10.1109/34.93808 · DOI · Paper page
  43. 10.1364/JOSAA.7.000923 · DOI · Paper page
  44. 10.1016/0262-8856(92)90015-U · DOI · Paper page
  45. 10.1364/JOSAA.2.000284 · DOI · Paper page
  46. 10.1109/CVPR.1996.517092 · DOI · Paper page
  47. itti, 1998, A Model of Saliency-Based Visual Attention for Rapid Scene Analysis, IEEE Trans Pattern Analysis and Machine Intelligence, 20, 1254, 10.1109/34.730558 · DOI · Paper page
  48. 10.1109/ICCV.1990.139492 · DOI · Paper page
  49. 10.1109/12.210173 · DOI · Paper page
  50. maffei, 1973, The Visual Cortex as a Spatial Frequency Analyser, Vision Research, 13, 1255, 10.1016/0042-6989(73)90201-0 · DOI · Paper page
  51. 10.1007/BF00318371 · DOI · Paper page
  52. mallat, 1989, A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE Trans Pattern Analysis and Machine Intelligence, 11, 647, 10.1109/34.192463 · DOI · Paper page
  53. 10.1364/JOSAA.4.002379 · DOI · Paper page
  54. ?ochman, 2005, Waldboost?Learning for Time Constrained Sequential Detection, Proc IEEE Conf Computer Vision and Pattern Recognition (CVPR)
  55. 10.1109/5.52200 · DOI · Paper page
  56. 10.1109/TPAMI.2009.144 · DOI · Paper page
  57. 10.1109/CVPR.2011.5995668 · DOI
  58. zhang, 2007, Multiple-Instance Pruning for Learning Efficient Cascade Detectors, Proc Advances in Neural Information Processing Systems (NIPS)
  59. 10.1109/CVPR.2005.310 · DOI · Paper page
  60. crowley, 2002, Fast Computation of Characteristic Scale Using a Half-Octave Pyramid, Proc Fourth Int?l Conf Scale-Space Theories in Computer Vision
  61. 10.1109/34.49051 · DOI · Paper page
  62. 10.1109/CVPR.2010.5539906 · DOI · Paper page
  63. 10.1109/ICVS.2006.9 · DOI

Cited by

See all 1,955

Metadata

Authors
Dollar, P., Appel, R., Belongie, S., & Perona, P.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2014-08
Volume
36
Issue
8
Pages
1532-1545
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
DOI
10.1109/tpami.2014.2300479
OpenAlex
W2125556102
Cited by
1,955
References
13
FWCI
206.23
Type
journal article
Language
en
Open access
closed
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)

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: Fast Feature Pyramids for Object Detection. https://app.cochat.ai/papers/10.1109/tpami.2014.2300479
The paper
Dollar, P., Appel, R., Belongie, S., & Perona, P. (2014). Fast Feature Pyramids for Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2014.2300479

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.