Meta-class features for large-scale object categorization on a budget

65 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.

Recognizing Image Style (2013, background): “The mc-bit feature [2] is a 15,000-dimensional bit vector feature learned as a non-linear combination of classifiers trained using existing features (e.”
Multi-class Open Set Recognition Using Probability of Inclusion (2014, methodology): “For multi-class recognition problems in computer vision, posterior probabilities are widely used to make decisions in applications such as pedestrian classification and orientation estimation [18], image retrieval [15], attribute fusion [42], part-based human tracking [47], large-scale multi-class o”
Network of Experts for Large-Scale Image Categorization (2016, background): “Another solution is to perform spectral clustering over the confusion matrix, as done in [38, 17, 3].”
Additive Quantization for Extreme Vector Compression (2014, methodology): “Here a classifier can be trained on a smaller set of images and then applied to a very large dataset of compressed image descriptors in order to find the images with the highest classification score [5, 4, 2].”