Investigating non-classical correlations between decision fused multi-modal documents

by   Sagar Uprety, et al.

Correlation has been widely used to facilitate various information retrieval methods such as query expansion, relevance feedback, document clustering, and multi-modal fusion. Especially, correlation and independence are important issues when fusing different modalities that influence a multi-modal information retrieval process. The basic idea of correlation is that an observable can help predict or enhance another observable. In quantum mechanics, quantum correlation, called entanglement, is a sort of correlation between the observables measured in atomic-size particles when these particles are not necessarily collected in ensembles. In this paper, we examine a multimodal fusion scenario that might be similar to that encountered in physics by firstly measuring two observables (i.e., text-based relevance and image-based relevance) of a multi-modal document without counting on an ensemble of multi-modal documents already labeled in terms of these two variables. Then, we investigate the existence of non-classical correlations between pairs of multi-modal documents. Despite there are some basic differences between entanglement and classical correlation encountered in the macroscopic world, we investigate the existence of this kind of non-classical correlation through the Bell inequality violation. Here, we experimentally test several novel association methods in a small-scale experiment. However, in the current experiment we did not find any violation of the Bell inequality. Finally, we present a series of interesting discussions, which may provide theoretical and empirical insights and inspirations for future development of this direction.


page 1

page 2

page 3

page 4


Multi-modal space structure: a new kind of latent correlation for multi-modal entity resolution

Multi-modal data is becoming more common than before because of big data...

Exploiting "Quantum-like Interference" in Decision Fusion for Ranking Multimodal Documents

Fusing and ranking multimodal information remains always a challenging t...

Efficient Large-Scale Multi-Modal Classification

While the incipient internet was largely text-based, the modern digital ...

CLIP Multi-modal Hashing: A new baseline CLIPMH

The multi-modal hashing method is widely used in multimedia retrieval. I...

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion

With the development of web technology, multi-modal or multi-view data h...

A Rich Recipe Representation as Plan to Support Expressive Multi Modal Queries on Recipe Content and Preparation Process

Food is not only a basic human necessity but also a key factor driving a...

Quantum Entanglement in Corpuses of Documents

We show that data collected from corpuses of documents violate the Claus...

Please sign up or login with your details

Forgot password? Click here to reset