Context based visual content verification

Martin Lukáč, Aigerim Bazarbciyeva, Michitaka Kameyama

2017

Full text Open access: Green Metadata (CSL-JSON)

DOI 10.1109/dt.2017.8024302

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

In this paper the intermediary visual content verification method based on multi-level co-occurrences is studied. The co-occurrence statistics are in general used to determine relational properties between objects based on information collected from data. As such these measures are heavily subject to relative number of occurrences and give only limited amount of accuracy when predicting objects in real world. In order to improve the accuracy of this method in the verification task, we include the context information such as location, type of environment etc. In order to train our model we provide new annotated dataset the Advanced Attribute VOC (AAVOC) that contains additional properties of the image. We show that the usage of context greatly improve the accuracy of verification with up to 16% improvement.