Temporal Image Caption Retrieval Competition -- Description and Results

TL;DR

This paper introduces a new multimodal task involving temporal data for image caption retrieval, based on historic newspapers, and presents a competition with analysis of the dataset and results.

Contribution

It presents the first competition on temporal multimodal retrieval using historic newspaper data, expanding the scope of multimodal retrieval tasks.

Findings

Dataset analysis and creation process detailed

Competition results showcasing current model performance

Insights into challenges of temporal multimodal retrieval

Abstract

Multimodal models, which combine visual and textual information, have recently gained significant recognition. This paper addresses the multimodal challenge of Text-Image retrieval and introduces a novel task that extends the modalities to include temporal data. The Temporal Image Caption Retrieval Competition (TICRC) presented in this paper is based on the Chronicling America and Challenging America projects, which offer access to an extensive collection of digitized historic American newspapers spanning 274 years. In addition to the competition results, we provide an analysis of the delivered dataset and the process of its creation.