+(91) 99007-25045
support@evolettechnologies.com
Learning of Multimodal Representations with Random Walks on the Click Graph
  • Learning of Multimodal Representations with Random Walks on the Click Graph

Learning of Multimodal Representations with Random Walks on the Click Graph

Sold By Final year Student Project
Categories: , Tags: , ,
  • Description
  • Reviews (0)

Product Description

Learning Multi-modal Representations Random Walks Click Graph

The most classic approaches tend to represent different modalities of media in the same feature space in multimedia information retrieval.Learning Multi-modal Representations Random Walks Click Graph.

With the click data collected from the users’ searching behavior, existing approaches take either one-to-one paired data like text-image pairs or ranking examples text-query-image and/or image-query-text ranking lists as training examples, which do not make full use of the click data, particularly the implicit connections among the data objects. The proposed system treat the click data as a large click graph, in which vertices are images/text queries and edges indicate the clicks between an image and a query.

Learning of multimodal representation from the perspective of encoding the explicit/implicit relevance relationship between the vertices in the click graph.Learning Multi-modal Representations Random Walks Click Graph.

By minimizing both the truncated random walk loss as well as the distance between the learned representation of vertices and their corresponding deep neural network output, the proposed model which is named multimodal random walk neural network (MRW-NN) can be applied to not only learn robust representation of the existing multimodal data in the click graph, but also deal with the unseen queries and images to support cross-modal retrieval. We evaluate the latent representation learned by MRW-NN on a public large-scale click log data set Clickture and further show that MRW-NN achieves much better cross-modal retrieval performance on the unseen queries/images than the other state-of-the-art methods.

Reviews

There are no reviews yet. Add a review