A retrieval-trained neural network produces word and phrase localization maps, reaching 51.06 pointing-game accuracy on Flickr30K Entities, the best reported score among weakly supervised methods.
Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In the traditional object recognition pipeline, descriptors are densely sampled over an image, pooled into a high dimensional non-linear representation and then passed to a classifier. In recent years, Fisher Vectors have proven empirically to be the leading representation for a large variety of applications. The Fisher Vector is typically taken as the gradients of the log-likelihood of descriptors, with respect to the parameters of a Gaussian Mixture Model (GMM). Motivated by the assumption that different distributions should be applied for different datasets, we present two other Mixture Models and derive their Expectation-Maximization and Fisher Vector expressions. The first is a Laplacian Mixture Model (LMM), which is based on the Laplacian distribution. The second Mixture Model presented is a Hybrid Gaussian-Laplacian Mixture Model (HGLMM) which is based on a weighted geometric mean of the Gaussian and Laplacian distribution. An interesting property of the Expectation-Maximization algorithm for the latter is that in the maximization step, each dimension in each component is chosen to be either a Gaussian or a Laplacian. Finally, by using the new Fisher Vectors derived from HGLMMs, we achieve state-of-the-art results for both the image annotation and the image search by a sentence tasks.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi Supervised Phrase Localization in a Bidirectional Caption-Image Retrieval Framework
A retrieval-trained neural network produces word and phrase localization maps, reaching 51.06 pointing-game accuracy on Flickr30K Entities, the best reported score among weakly supervised methods.