IEEE Transactions on Pattern Analysis and Machine Intelligence

3,551 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Language Is Not All You Need: Aligning Perception with Language Models (2023, methodology): “We use the test set of COCO Karpathy split [KFF17], which re-partitions the train2014 and val2014 images [LMB14] into 113,287, 5,000, and 5,000 for the training set, validation set, and test set, respectively.”
Proposal-Free Network for Instance-Level Object Segmentation (2015, neutral): “The network can be trained by back-propagation and stochastic gradient descent (SGD) [19].”
Limitations of Principal Components Analysis for Hyperspectral Target Recognition (2008, methodology): “PRINCIPAL components analysis (PCA) is a popular tool for dimensionality reduction in various data analysis schemes [1]–[3].”
Matching 2.5D face scans to 3D models (2006, methodology): “In order to apply the subspace analysis based on the facial appearance, many training samples, which are aligned with the test sample, are needed [40], [43].”
Evaluating Complexity, Code Churn, and Developer Activity Metrics as Indicators of Software Vulnerabilities (2011, background): “Discriminant analysis has widespread applications, including facial recognition [21, 37].”