2012 · 135 citations · 39 references
ComputingComputer ScienceVision ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningFeature DetectionPattern RecognitionRepresentation LearningVideo AnalysisVisual TrackingClassification AccuracyDeep Learning-based ClassificationHierarchical Network StructureInvariant Representation LearningSalient Feature ExtractionSalient Feature IdentificationSalient Region DetectionSpatiotemporal Feature Learning
We apply salient feature detection and tracking in videos to simulate fixations and smooth pursuit in human vision. With tracked sequences as input, a hierarchical network of modules learns invariant features using a temporal slowness constraint. The network encodes invariance which are increasingly complex with hierarchy. Although learned from videos, our features are spatial instead of spatial-temporal, and well suited for extracting features from still images. We applied our features to four datasets (COIL-100, Caltech 101, STL-10, PubFig), and observe a consistent improvement of 4 % to 5 % in classification accuracy. With this approach, we achieve state-of-the-art recognition accuracy 61 % on STL-10 dataset. 1
39
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
Andrea Vedaldi, Brian Fulkerson · 2010 · 2.7K citations
An analysis of single-layer networks in unsupervised feature learning
Adam Coates, Andrew Y. Ng, Honglak Lee · 2011 · 2.5K citations