by gooly (Li Yang Ku)
Although it’s not always the case that a paper cited more contributes more to the field, a highly cited paper usually indicates that something interesting have been discovered. The following are the papers to my knowledge being cited the most in Computer Vision. (updated on 11/24/2013) If you want your “friend’s” paper listed here, just comment below.
Cited by 21528 + 6830 (Object recognition from local scale-invariant features)
Distinctive image features from scale-invariant keypoints
DG Lowe – International journal of computer vision, 2004
Cited by 22181
A threshold selection method from gray-level histograms
N Otsu – Automatica, 1975
Cited by 17671
A theory for multiresolution signal decomposition: The wavelet representation
SG Mallat – Pattern Analysis and Machine Intelligence, IEEE …, 1989
Cited by 17611
A computational approach to edge detection
J Canny – Pattern Analysis and Machine Intelligence, IEEE …, 1986
Cited by 15422
M Kass, A Witkin, Demetri Terzopoulos – International journal of computer …, 1988
Cited by 15188
Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images
Geman and Geman – Pattern Analysis and Machine …, 1984
Cited by 11630+ 4138 (Face Recognition using Eigenfaces)
Turk and Pentland, Journal of cognitive neuroscience Vol. 3, No. 1, Pages 71-86, 1991 (9358 citations)
Cited by 8788
B.K.P. Horn and B.G. Schunck, Artificial Intelligence, vol 17, pp 185-203, 1981
Cited by 8559
Scale-space and edge detection using anisotropic diffusion
P Perona, J Malik
Pattern Analysis and Machine Intelligence, IEEE Transactions on 12 (7), 629-639
Cited by 8432 + 5901 (Robust real time face detection)
Rapid object detection using a boosted cascade of simple features
P Viola, M Jones
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the …
Cited by 8351
TF Chan, LA Vese – IEEE Transactions on image processing, 2001
Cited by 7517
An iterative image registration technique with an application to stereo vision
B. D. Lucas and T. Kanade (1981), An iterative image registration technique with an application to stereo vision. Proceedings of Imaging Understanding Workshop, pages 121–130
Cited by 7979
Normalized cuts and image segmentation
J Shi, J Malik
Pattern Analysis and Machine Intelligence, IEEE Transactions on 22 (8), 888-905
Cited by 6658
Histograms of oriented gradients for human detection
N Dalal… – … 2005. CVPR 2005. IEEE Computer Society …, 2005
Cited by 6528
Mean shift: A robust approach toward feature space analysis
D Comaniciu, P Meer – … Analysis and Machine Intelligence, …, 2002
Cited by 5130
The Laplacian pyramid as a compact image code
Burt and Adelson, – Communications, IEEE Transactions on, 1983
Cited by 4987
Performance of optical flow techniques
JL Barron, DJ Fleet, SS Beauchemin – International journal of computer vision, 1994
Cited by 4870
Condensation—conditional density propagation for visual tracking
M Isard and Blake – International journal of computer vision, 1998
Cited by 4884
Shi and Tomasi , 1994. Proceedings CVPR’94., 1994 IEEE, 1994
Cited by 4875
A model of saliency-based visual attention for rapid scene analysis
L Itti, C Koch, E Niebur, Analysis and Machine Intelligence, 1998
Cited by 4769
A performance evaluation of local descriptors
K Mikolajczyk, C Schmid
Pattern Analysis and Machine Intelligence, IEEE Transactions on 27 (10 ..
Cited by 4070
Fast approximate energy minimization via graph cuts
Y Boykov, O Veksler, R Zabih
Pattern Analysis and Machine Intelligence, IEEE Transactions on 23 (11 .
Cited by 3634
Surf: Speeded up robust features
H Bay, T Tuytelaars… – Computer Vision–ECCV 2006, 2006
Cited by 3702
Neural network-based face detection
HA Rowley, S Baluja, Takeo Kanade – Pattern Analysis and …, 1998
Cited by 2869
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
BA Olshausen – Nature, 1996
Cited by 3832
Shape matching and object recognition using shape contexts
S Belongie, J Malik, J Puzicha
Pattern Analysis and Machine Intelligence, IEEE Transactions on 24 (4), 509-522
Cited by 3271
Shape modeling with front propagation: A level set approach
R Malladi, JA Sethian, BC Vemuri – Pattern Analysis and Machine Intelligence, 1995
Cited by 2547
JJ Koenderink – Biological cybernetics, 1984 – Springer
Cited by 2361
Shape and motion from image streams under orthography: a factorization method
Tomasi and Kanade – International Journal of Computer Vision, 1992
Cited by 2632
TF Cootes, GJ Edwards… – Pattern Analysis and …, 2001
Cited by 2704
Scale & affine invariant interest point detectors
K Mikolajczyk, C Schmid
International journal of computer vision 60 (1), 63-86
Cited by 2025
Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach
PE Debevec, CJ Taylor, J Malik
Proceedings of the 23rd annual conference on Computer graphics and …
Cited by 1978
Feature extraction from faces using deformable templates
AL Yuille, PW Hallinan… – International journal of computer …, 1992
Cited by 2048
Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation
SC Zhu, A Yuille
Pattern Analysis and Machine Intelligence, IEEE Transactions on 18 (9), 884-900
Cited by 2948
Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories
S Lazebnik, C Schmid, J Ponce
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society …
Cited by 2206
Face detection in color images
RL Hsu, M Abdel-Mottaleb, AK Jain – IEEE transactions on pattern …, 2002
Cited by 2148
Efficient graph-based image segmentation
PF Felzenszwalb… – International Journal of Computer …, 2004
Cited by 2112
Visual categorization with bags of keypoints
G Csurka, C Dance, L Fan, J Willamowski, C Bray – Workshop on statistical …, 2004
Cited by 1868
Object class recognition by unsupervised scale-invariant learning
R Fergus, P Perona, A Zisserman
Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE …
Cited by 1945
Recovering high dynamic range radiance maps from photographs
PE Debevec, J Malik
ACM SIGGRAPH 2008 classes, 31
Cited by 1896
A comparison of affine region detectors
K Mikolajczyk, T Tuytelaars, C Schmid, A Zisserman, J Matas, F Schaffalitzky …
International journal of computer vision 65 (1), 43-72
Cited by 1880
A bayesian hierarchical model for learning natural scene categories
L Fei-Fei… – Computer Vision and Pattern …, 2005
Note that the papers I listed here are just the ones that came up to my mind, let me know if I missed any important publications; I would be happy to make the list more complete. Also check out the website I made for organizing papers visually.
the Serious Computer Vision Blog 
“Fast approximate energy minimization via graph cuts” has over 2k citations.
LikeLike
Thanks, added that
LikeLike
[…] by my M.S adviser Alan Yuille. In addition, the paper has 1651 citations and is listed in my most cited computer vision paper list. Apparently you need to publish high quality papers to get into the cartoon industry; this […]
LikeLike
B. D. Lucas and T. Kanade (1981), An iterative image registration technique with an application to stereo vision. Proceedings of Imaging Understanding Workshop, pages 121–130
B.K.P. Horn and B.G. Schunck, “Determining optical flow.” Artificial Intelligence, vol 17, pp 185-203, 1981
LikeLike
Thanks, added
LikeLike
Eigenfaces:
Turk and Pentland, Eigenfaces for Recognition, Vol. 3, No. 1, Pages 71-86, 1991 (9358 citations)
Turk and Pentland, Face recognition using eigenfaces, CVPR, 1991 (3206 citations)
LikeLike
My guess is that the Lucas-Kanade and Schunck-Horn papers have more citations but are vastly underestimated because they were published in vision’s “dark ages” (before 1988, indexing of IEEE vision papers begin in 1987). Although they appeared 1981, they still remain standard references to this day.
LikeLike
Right, without the “dark ages” the list would be far much longer. What I intended to do at first was to make a list about “the most cited object recognition papers” but I ended up using “the most cited papers in computer vision” since it sounds cooler and more searchable. I spent some time working on a website to organize papers, but stop working on it after I failed to get into PhD programs.
LikeLike
Correction: indexing of IEEE vision papers begin in 1988
LikeLike
Burt and Adelson, The Laplacian pyramid as a compact image code, IEEE Transactions on Communications, 1983. (4004 citations)
Mallat, A theory for multiresolution signal decomposition: The wavelet representation, PAMI, 1989 (14455 citations)
Isard and Blake, Condensation—conditional density propagation for visual tracking, IJCV, 1998 (3897 citations)
Shi and Tomasi, Good Features to Track, CVPR 1994 (3746 citations)
Tomasi and Kanade,Shape and motion from image streams under orthography: a factorization method, IJCV, 1992 (2147 citations)
Geman and Geman, Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images, PAMI, 1984 (12841 citations)
J. Canny, A computational approach to edge detection, PAMI, 1986 (13235 citations)
JJ Koenderink, The structure of images, Biological cybernetics, 1984 (2151 citations)
LikeLike
Gee thanks, that’s quiet a lot, some of them I never heard of. Should read them when I have time
LikeLike
It’s worth remembering that the majority of these papers are highly cited, not because they report definitive solutions to problems, but because the papers launched discourses about important problems, hence the high citations. For example Horn’s optical flow sucks for motion analysis. I mean — really — you’re not going to use optical flow on real world video streams, are you, what with changing illumination, etc?
LikeLike
Right, many papers are highly cited because of opening a new field to research on. But that is equally valuable to a paper that has a break through solution.
LikeLike
I agree the papers have value. But I think today you can completely ignore some of them, like Turk/Pentland’s Eigenfaces crap. Viola/Jones and its descendants solve the problem very well, and the Eigenfaces nonsense can be happily forgotten. It’s not as though they invented PCA or anything!
LikeLike
But I also wanted to add that KGD has some excellent choices, and that, given your interest, you clearly belong in a PhD program. Where did you apply? There are lots of good departments not in the USN&WR Top Ten that wouldn’t be career-limiting.
LikeLike
I am beginning a literature survey of computer vision documents. Do have a page of beginning or a primer articles for computer vision?
Where do I start?
Thanks
Geri
LikeLike
If you have a specific topic to work on, you should be able to find some survey paper on google scholar, otherwise Wikipedia is a good start.
LikeLike
Hi.
May I suggest the paper entitled “Visual categorization with bags of keypoints” by G Csurka, C Dance, L Fan, J Willamowski and C Bray which appeared in the ECCV 2004 workshop on statistical learning in computer vision? it has 2,112 citations according to Google scholar.
Cheers,
Florent
LikeLike
I just added it. Thanks for suggesting!
LikeLike
Mean shift: A robust approach toward feature space analysis
Very interesting paper..for low level vision problems
LikeLike
Added that, Thanks
LikeLike
A model of -based visual attention for rapid scene analysis
over 4k
LikeLike
Thanks, list updated
LikeLike
[…] social science, organizational engineering, wearable computing (Google Glass), image understanding, and modern biometrics. His research has been featured in Nature, Science, and Harvard Business Review, as well as being […]
LikeLike
[…] of Oriented Gradient (HOG) are an extension of these edge detectors. An example of HOG is the quite successful paper on pedestrian detection “Histograms of oriented gradients for human detection” (See […]
LikeLike
Here are some of advisor’s papers:
Fingerprint image enhancement: algorithm and performance evaluation
L Hong, Y Wan, A Jain
Pattern Analysis and Machine Intelligence, IEEE Transactions on 20 (8), 777-789
1998 (2046 citations)
Statistical pattern recognition: A review
AK Jain, RPW Duin, J Mao
Pattern Analysis and Machine Intelligence, IEEE Transactions on 22 (1), 4-37
2000 (4995 citations)
Face detection in color images
RL Hsu, M Abdel-Mottaleb, AK Jain
Pattern Analysis and Machine Intelligence, IEEE Transactions on 24 (5), 696-706
2002 (2206 citations)
LikeLike
Thanks, I added the face detection paper. I kind of hesitated on adding the other two papers though; the boundary of computer vision is not well defined and the other two papers kind of lie on the edge of what I view as computer vision research.
LikeLike
Shape modeling with front propagation: A level set approach
PAMI’95
Ravi Malladi, James A Sethian, Baba C Vemuri
Cited by 3271 (as of Nov 2014, according to Google Scholar)
LikeLike
Shape modeling with front propagation: A level set approach
PAMI’95
Ravi Malladi, James A Sethian, Baba C Vemuri
Cited by 3271 (as of Nov 2014, according to Google Scholar)
LikeLike
Added, thanks!
LikeLike
Performance of optical flow techniques, John L Barron, David J Fleet, SS Beauchemin, IJCV
has been cited more than 5000 times and started a trend towards more quantitative analysis of vision algorithms (not just flow).
http://scholar.google.de/citations?view_op=view_citation&hl=de&user=njOmQFsAAAAJ&citation_for_view=njOmQFsAAAAJ:HE397vMXCloC
LikeLike
I added that, thanks Michael!
LikeLike
“Gradient-Based Learning Applied to Document Recognition”, this work might be the most cited paper in “Deep Learning” communities.
LikeLike
This list is made before deep learning became popular in computer vision. I might open a new list for deep learning related papers.
LikeLike
[…] of an image for segmentation. This is based on the following paper which is one of the most cited papers in Computer Vision. If you are starting to do research in computer vision related fields it is a good idea to […]
LikeLike
Nice idea to start a deep learning list. Although can still add the most prominent papers here.
May I suggest to add :
Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. “Imagenet classification with deep convolutional neural networks.” Advances in neural information processing systems. 2012. 5000+ citations
LikeLike
[…] 2012 I started a list on the most cited papers in the field of computer vision. I try to keep the list focus on researches that relate […]
LikeLike
A Threshold Selection Method from Gray-Level Histograms
Otsu 1979
cited by 22k
Active contour without edges
Chan Vese 2001
cited by 8.5k
LikeLike
Thanks
LikeLike
Optimal Approximations by Piecewise Smooth Functions and
Associated Variational Problems
Mumford, Shah 1989
FRONTS PROPAGATING WITH CURVATURE DEPENDENT SPEED:
ALGORITHMS BASED ON HAMILTON-JACOB1 FORMULATIONS
Osher, Sethian 1987
Object detection with discriminatively trained part-based models
Felzenszwalb, Girshick
LikeLike
Optimal Approximations by Piecewise Smooth Functions and
Associated Variational Problems
Mumford, Shah 1989
FRONTS PROPAGATING WITH CURVATURE DEPENDENT SPEED:
ALGORITHMS BASED ON HAMILTON-JACOB1 FORMULATIONS
Osher, Sethian 1987
Object detection with discriminatively trained part-based models
Felzenszwalb, Girshick
LikeLike
5
LikeLike
[…] social science, organizational engineering, wearable computing (Google Glass), image understanding, and modern biometrics. His most recent books are Social Physics, published by Penguin Press, and Honest Signals, […]
LikeLike
[…] social science, organizational engineering, wearable computing (Google Glass), image understanding, and modern biometrics. His most recent books are Social Physics, published by Penguin Press, and Honest Signals, […]
LikeLike
[…] social science, organizational engineering, wearable computing(Google Glass), image understanding, and modern biometrics. His research has been featured in Nature, Science, and Harvard Business Review, as well as being […]
LikeLike
[…] social science, organizational engineering, wearable computing (Google Glass), image understanding, and modern biometrics. His most recent books are Building the New Economy and Trusted Data, both published by MIT […]
LikeLike
[…] social science, organizational engineering, wearable computing (Google Glass), image understanding, and modern biometrics. His most recent books are Building the New Economy and Trusted Data, both published by MIT […]
LikeLike