T
Thomas Mensink
Researcher at Google
Publications - 98
Citations - 8650
Thomas Mensink is an academic researcher from Google. The author has contributed to research in topics: Contextual image classification & Support vector machine. The author has an hindex of 29, co-authored 93 publications receiving 7730 citations. Previous affiliations of Thomas Mensink include French Institute for Research in Computer Science and Automation & Xerox.
Papers
More filters
Book ChapterDOI
Improving the fisher kernel for large-scale image classification
TL;DR: In an evaluation involving hundreds of thousands of training images, it is shown that classifiers learned on Flickr groups perform surprisingly well and that they can complement classifier learned on more carefully annotated datasets.
Journal ArticleDOI
Image Classification with the Fisher Vector: Theory and Practice
TL;DR: This work proposes to use the Fisher Kernel framework as an alternative patch encoding strategy: it describes patches by their deviation from an “universal” generative Gaussian mixture model, and reports experimental results showing that the FV framework is a state-of-the-art patch encoding technique.
Proceedings ArticleDOI
TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation
TL;DR: This work proposes TagProp, a discriminatively trained nearest neighbor model that allows the integration of metric learning by directly maximizing the log-likelihood of the tag predictions in the training set, and introduces a word specific sigmoidal modulation of the weighted neighbor tag predictions to boost the recall of rare words.
Journal ArticleDOI
Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost
TL;DR: Two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers are considered, and a new metric learning approach is introduced for the latter, and an extension of the NCM classifier is introduced to allow for richer class representations.
Book ChapterDOI
Metric learning for large scale image classification: generalizing to new classes at near-zero cost
TL;DR: The goal is to devise classifiers which can incorporate images and classes on-the-fly at (near) zero cost and to explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers.