Top Cited Papers: CVPR 2004

Curated Papers:

PCA-SIFT: a more distinctive representation for local image descriptors

Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) recently evaluated a variety of approaches and identified the SIFT [D. G. Lowe, 1999] algorithm as being the most resistant to common image deformations. This paper examines (and improves upon) the local image descriptor used by SIFT. Like SIFT, our descriptors encode the salient aspects of the image gradient in the feature point’s neighborhood; however, instead of using SIFT’s smoothed weighted histograms, we apply principal components analysis (PCA) to the normalized gradient patch. Our experiments demonstrate that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation. We also present results showing that using these descriptors in an image retrieval application results in increased accuracy and faster matching.

Learning object detection from a small number of examples: the importance of good features

Face detection systems have recently achieved high detection rates and real-time performance. However, these methods usually rely on a huge training database (around 5,000 positive examples for good performance). While such huge databases may be feasible for building a system that detects a single object, it is obviously problematic for scenarios where multiple objects (or multiple views of a single object) need to be detected. Indeed, even for multi-viewface detection the performance of existing systems is far from satisfactory. In this work we focus on the problem of learning to detect objects from a small training database. We show that performance depends crucially on the features that are used to represent the objects. Specifically, we show that using local edge orientation histograms (EOH) as features can significantly improve performance compared to the standard linear features used in existing systems. For frontal faces, local orientation histograms enable state of the art performance using only a few hundred training examples. For profile view faces, local orientation histograms enable learning a system that seems to outperform the state of the art in real-time systems even with a small number of training examples.

Full List:

  1. PCA-SIFT: a more distinctive representation for local image descriptors Yan Ke;R. Sukthankar Publication Year: 2004,Page(s):II – II Cited by: Papers (459) | Patents (27)
  2. Learning methods for generic object recognition with invariance to pose and lighting Y. LeCun;Fu Jie Huang;L. Bottou Publication Year: 2004,Page(s):II – 104 Vol.2 Cited by: Papers (417) | Patents (16)
  3. Multiple Bernoulli relevance models for image and video annotation S.L. Feng;R. Manmatha;V. Lavrenko Publication Year: 2004,Page(s):II – II Cited by: Papers (364) | Patents (13)
  4. Motion-based background subtraction using adaptive kernel density estimation A. Mittal;N. Paragios Publication Year: 2004,Page(s):II – II Cited by: Papers (288) | Patents (8)
  5. Sharing features: efficient boosting procedures for multiclass object detection A. Torralba;K.P. Murphy;W.T. Freeman Publication Year: 2004,Page(s):II – II Cited by: Papers (283) | Patents (6)
  6. Is bottom-up attention useful for object recognition? U. Rutishauser;D. Walther;C. Koch;P. Perona Publication Year: 2004,Page(s):II – II Cited by: Papers (278) | Patents (8)
  7. Detecting unusual activity in video Hua Zhong;Jianbo Shi;M. Visontai Publication Year: 2004,Page(s):II – II Cited by: Papers (240) | Patents (6)
  8. Inferring 3D body pose from silhouettes using activity manifold learning A. Elgammal;Chan-Su Lee Publication Year: 2004,Page(s):II – II Cited by: Papers (197) | Patents (9) )
  9. Learning object detection from a small number of examples: the importance of good features K. Levi;Y. Weiss Publication Year: 2004,Page(s):II – II Cited by: Papers (191) | Patents (8)
  10. Names and faces in the news T.L. Berg;A.C. Berg;J. Edwards;M. Maire;R. White;Yee-Whye Teh;E. Learned-Miller;D.A. Forsyth Publication Year: 2004,Page(s):II – II Cited by: Papers (169) | Patents (6) )
  11. Bridging the gaps between cameras D. Makris;T. Ellis;J. Black Publication Year: 2004,Page(s):II – II Cited by: Papers (167) | Patents (5)
  12. 3D human pose from silhouettes by relevance vector regression A. Agarwal;B. Triggs Publication Year: 2004,Page(s):II – II Cited by: Papers (161) | Patents (21) )
  13. Tracking multiple humans in crowded environment Tao Zhao;R. Nevatia Publication Year: 2004,Page(s):II – II Cited by: Papers (157) | Patents (5)
  14. Recovering human body configurations: combining segmentation and recognition G. Mori;Xiaofeng Ren;A.A. Efros;J. Malik Publication Year: 2004,Page(s):II – II Cited by: Papers (143) | Patents (9)
  15. Multiscale conditional random fields for image labeling Xuming He;R.S. Zemel;M.A. Carreira-Perpinan Publication Year: 2004,Page(s):II – II Cited by: Papers (129) | Patents (4)
  16. A discriminative feature space for detecting and recognizing faces A. Hadid;M. Pietikainen;T. Ahonen Publication Year: 2004,Page(s):II – II Cited by: Papers (122) | Patents (1)
  17. Detecting and reading text in natural scenes Xiangrong Chen;A.L. Yuille Publication Year: 2004,Page(s):II – II Cited by: Papers (116) | Patents (34) )
  18. Color lines: image specific color representation I. Omer;M. Werman Publication Year: 2004,Page(s):II – II Cited by: Papers (106) | Patents (29)
  19. Radiometric calibration from a single image S. Lin;Jinwei Gu;S. Yamazaki;Heung-Yeung Shum Publication Year: 2004,Page(s):II – II Cited by: Papers (88) | Patents (10)
  20. What image information is important in silhouette-based gait recognition? G.V. Veres;L. Gordon;J.N. Carter;M.S. Nixon Publication Year: 2004,Page(s):II – II Cited by: Papers (80)
  21. Distortion estimation techniques in solving visual CAPTCHAs G. Moy;N. Jones;C. Harkless;R. Potter Publication Year: 2004,Page(s):II – II Cited by: Papers (78) | Patents (2)
  22. Parts-based 3D object classification D. Huber;A. Kapuria;R. Donamukkala;M. Hebert Publication Year: 2004,Page(s):II – II Cited by: Papers (78)
  23. Scale-invariant shape features for recognition of object categories F. Jurie;C. Schmid Publication Year: 2004,Page(s):II – II Cited by: Papers (77) | Patents (3)
  24. Feature-centric evaluation for efficient cascaded object detection H. Schneiderman Publication Year: 2004,Page(s):II – II Cited by: Papers (75) | Patents (26)
  25. Motion segmentation with missing data using PowerFactorization and GPCA R. Vidal;R. Hartley Publication Year: 2004,Page(s):II – II Cited by: Papers (75) | Patents (21)

https://ieeexplore.ieee.org/xpl/conhome/9183/proceeding?sortType=paper-citations

Leave a Reply Cancel reply