| # | Title | Journal | Year | Citations |
|---|
| 1 | Long Short-Term Memory | Neural Computation | 1997 | 58,553 |
| 2 | Distinctive Image Features from Scale-Invariant Keypoints | International Journal of Computer Vision | 2004 | 42,314 |
| 3 | Support-vector networks | Machine Learning | 1995 | 38,107 |
| 4 | U-Net: Convolutional Networks for Biomedical Image Segmentation | Lecture Notes in Computer Science | 2015 | 27,139 |
| 5 | LIBSVM | ACM Transactions on Intelligent Systems and Technology | 2011 | 25,138 |
| 6 | ImageNet Large Scale Visual Recognition Challenge | International Journal of Computer Vision | 2015 | 24,215 |
| 7 | A Computational Approach to Edge Detection | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1986 | 21,603 |
| 8 | Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2017 | 20,130 |
| 9 | Bagging predictors | Machine Learning | 1996 | 18,759 |
| 10 | SMOTE: Synthetic Minority Over-sampling Technique | Journal of Artificial Intelligence Research | 0 | 17,022 |
| 11 | A theory for multiresolution signal decomposition: the wavelet representation | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1989 | 16,677 |
| 12 | Multilayer feedforward networks are universal approximators | Neural Networks | 1989 | 16,040 |
| 13 | An introduction to ROC analysis | Pattern Recognition Letters | 2006 | 14,987 |
| 14 | Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1984 | 13,839 |
| 15 | Snakes: Active contour models | International Journal of Computer Vision | 1988 | 13,615 |
| 16 | A method for registration of 3-D shapes | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1992 | 13,602 |
| 17 | Microsoft COCO: Common Objects in Context | Lecture Notes in Computer Science | 2014 | 12,775 |
| 18 | Deep learning in neural networks: An overview | Neural Networks | 2015 | 12,685 |
| 19 | A Fast Learning Algorithm for Deep Belief Nets | Neural Computation | 2006 | 12,682 |
| 20 | Multiresolution gray-scale and rotation invariant texture classification with local binary patterns | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2002 | 12,183 |
| 21 | Intuitionistic fuzzy sets | Fuzzy Sets and Systems | 1986 | 12,130 |
| 22 | The Pascal Visual Object Classes (VOC) Challenge | International Journal of Computer Vision | 2010 | 12,097 |
| 23 | Induction of decision trees | Machine Learning | 1986 | 12,034 |
| 24 | DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2018 | 11,963 |
| 25 | SSD: Single Shot MultiBox Detector | Lecture Notes in Computer Science | 2016 | 11,879 |
| 26 | Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers | Foundations and Trends in Machine Learning | 2010 | 11,791 |
| 27 | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2017 | 11,162 |
| 28 | The Unity and Diversity of Executive Functions and Their Contributions to Complex “Frontal Lobe” Tasks: A Latent Variable Analysis | Cognitive Psychology | 2000 | 11,093 |
| 29 | Normalized cuts and image segmentation | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2000 | 10,785 |
| 30 | A feature-integration theory of attention | Cognitive Psychology | 1980 | 10,634 |
| 31 | Extreme learning machine: Theory and applications | Neurocomputing | 2006 | 10,570 |
| 32 | Robust Real-Time Face Detection | International Journal of Computer Vision | 2004 | 10,533 |
| 33 | A flexible new technique for camera calibration | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2000 | 10,514 |
| 34 | The concept of a linguistic variable and its application to approximate reasoning—I | Information Sciences | 1975 | 10,321 |
| 35 | Scale-space and edge detection using anisotropic diffusion | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1990 | 9,662 |
| 36 | Eigenfaces vs. Fisherfaces: recognition using class specific linear projection | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1997 | 9,612 |
| 37 | Determining optical flow | Artificial Intelligence | 1981 | 9,134 |
| 38 | A model of saliency-based visual attention for rapid scene analysis | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1998 | 9,026 |
| 39 | Mean shift: a robust approach toward feature space analysis | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2002 | 8,904 |
| 40 | Representation Learning: A Review and New Perspectives | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2013 | 8,225 |
| 41 | Q-learning | Machine Learning | 1992 | 8,093 |
| 42 | Robust Face Recognition via Sparse Representation | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2009 | 8,010 |
| 43 | An Information-Maximization Approach to Blind Separation and Blind Deconvolution | Neural Computation | 1995 | 7,791 |
| 44 | Object Detection with Discriminatively Trained Part-Based Models | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2010 | 7,725 |
| 45 | Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2005 | 7,719 |
| 46 | Least Squares Support Vector Machine Classifiers | Neural Processing Letters | 1999 | 7,709 |
| 47 | Backpropagation Applied to Handwritten Zip Code Recognition | Neural Computation | 1989 | 7,701 |
| 48 | Fuzzy sets as a basis for a theory of possibility | Fuzzy Sets and Systems | 1978 | 7,654 |
| 49 | Availability: A heuristic for judging frequency and probability | Cognitive Psychology | 1973 | 7,519 |
| 50 | Particle swarm optimization | Swarm Intelligence | 2007 | 7,503 |
| 51 | CBAM: Convolutional Block Attention Module | Lecture Notes in Computer Science | 2018 | 7,331 |
| 52 | Gene Selection for Cancer Classification using Support Vector Machines | Machine Learning | 2002 | 7,229 |
| 53 | SLIC Superpixels Compared to State-of-the-Art Superpixel Methods | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2012 | 7,142 |
| 54 | Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment | Journal of the ACM | 1973 | 7,074 |
| 55 | Wrappers for feature subset selection | Artificial Intelligence | 1997 | 6,993 |
| 56 | Induction of Decision Trees | Machine Learning | 1986 | 6,920 |
| 57 | Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2015 | 6,914 |
| 58 | Identification and control of dynamical systems using neural networks | IEEE Transactions on Neural Networks | 1990 | 6,837 |
| 59 | Independent component analysis: algorithms and applications | Neural Networks | 2000 | 6,796 |
| 60 | Random effects structure for confirmatory hypothesis testing: Keep it maximal | Journal of Memory and Language | 2013 | 6,772 |
| 61 | Data clustering: 50 years beyond K-means | Pattern Recognition Letters | 2010 | 6,687 |
| 62 | Support-Vector Networks | Machine Learning | 1995 | 6,650 |
| 63 | Authoritative sources in a hyperlinked environment | Journal of the ACM | 1999 | 6,521 |
| 64 | Nonlinear Component Analysis as a Kernel Eigenvalue Problem | Neural Computation | 1998 | 6,336 |
| 65 | Finding Structure in Time | Cognitive Science | 1990 | 6,281 |
| 66 | Image Super-Resolution Using Deep Convolutional Networks | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2016 | 6,132 |
| 67 | Mixed-effects modeling with crossed random effects for subjects and items | Journal of Memory and Language | 2008 | 6,119 |
| 68 | k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY | International Journal of Uncertainty, Fuzziness and Knowlege-Based Systems | 2002 | 6,011 |
| 69 | Training feedforward networks with the Marquardt algorithm | IEEE Transactions on Neural Networks | 1994 | 5,993 |
| 70 | Visualizing and Understanding Convolutional Networks | Lecture Notes in Computer Science | 2014 | 5,890 |
| 71 | Laplacian Eigenmaps for Dimensionality Reduction and Data Representation | Neural Computation | 2003 | 5,873 |
| 72 | A comparative study of texture measures with classification based on featured distributions | Pattern Recognition | 1996 | 5,753 |
| 73 | A Cluster Separation Measure | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1979 | 5,697 |
| 74 | Fast approximate energy minimization via graph cuts | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2001 | 5,660 |
| 75 | Learning long-term dependencies with gradient descent is difficult | IEEE Transactions on Neural Networks | 1994 | 5,569 |
| 76 | Learning Deep Architectures for AI | Foundations and Trends in Machine Learning | 2009 | 5,547 |
| 77 | Vision meets robotics: The KITTI dataset | International Journal of Robotics Research | 2013 | 5,483 |
| 78 | Reinforcement Learning: An Introduction | IEEE Transactions on Neural Networks | 1998 | 5,466 |
| 79 | Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning | Proceedings of the AAAI Conference on Artificial Intelligence | 2017 | 5,434 |
| 80 | A performance evaluation of local descriptors | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2005 | 5,399 |
| 81 | GSA: A Gravitational Search Algorithm | Information Sciences | 2009 | 5,379 |
| 82 | Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation | Lecture Notes in Computer Science | 2018 | 5,282 |
| 83 | A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms | International Journal of Computer Vision | 2002 | 5,271 |
| 84 | Fully Convolutional Networks for Semantic Segmentation | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2017 | 5,229 |
| 85 | Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope | International Journal of Computer Vision | 2001 | 5,192 |
| 86 | Fast and robust fixed-point algorithms for independent component analysis | IEEE Transactions on Neural Networks | 1999 | 5,183 |
| 87 | A comparison of methods for multiclass support vector machines | IEEE Transactions on Neural Networks | 2002 | 5,170 |
| 88 | Stacked generalization | Neural Networks | 1992 | 5,157 |
| 89 | Shape matching and object recognition using shape contexts | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2002 | 5,089 |
| 90 | Real-Time Obstacle Avoidance for Manipulators and Mobile Robots | International Journal of Robotics Research | 1986 | 5,055 |
| 91 | Reinforcement Learning: A Survey | Journal of Artificial Intelligence Research | 0 | 5,055 |
| 92 | The use of the area under the ROC curve in the evaluation of machine learning algorithms | Pattern Recognition | 1997 | 5,024 |
| 93 | Face Description with Local Binary Patterns: Application to Face Recognition | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2006 | 4,914 |
| 94 | Basic objects in natural categories | Cognitive Psychology | 1976 | 4,856 |
| 95 | The random subspace method for constructing decision forests | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1998 | 4,844 |
| 96 | Extremely randomized trees | Machine Learning | 2006 | 4,796 |
| 97 | Introduction to special issue on large-scale machine learning | ACM Transactions on Intelligent Systems and Technology | 2011 | 4,794 |
| 98 | Efficient Graph-Based Image Segmentation | International Journal of Computer Vision | 2004 | 4,789 |
| 99 | Statistical pattern recognition: a review | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2000 | 4,766 |
| 100 | Content-based image retrieval at the end of the early years | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2000 | 4,753 |
