# Evaluating the Representational Hub of Language and Vision Models

Source: [Evaluating the Representational Hub of Language and Vision Models](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b344>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:30:43.473Z

Authors: Ravi Shekhar, Ece Takmaz, Raquel Fern\\'andez, Raffaella Bernardi

Published: 2019-04-12T05:18:35.000Z

## Abstract

The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the \`Hub and Spoke' architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations learned by the encoder, we use two kinds of analyses. First, we evaluate the encoder pre-trained on the different vision-and-language tasks on an existing diagnostic task designed to assess multimodal semantic understanding. Second, we carry out a battery of analyses aimed at studying how the encoder merges and exploits the two modalities.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.06038>)

[PDF](<https://arxiv.org/pdf/1904.06038.pdf>)
