# Visual Dialogue without Vision or Dialogue

Source: [Visual Dialogue without Vision or Dialogue](<https://www.sota2.com/research/paper/68fa66941e209131cea11118>)

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

Data updated: 2025-10-25T21:53:21.106Z

Authors: Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H.S. Torr

Published: 2018-12-16T08:18:37.000Z

## Abstract

We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli. To do so, we develop an embarrassingly simple method based on Canonical Correlation Analysis (CCA) that, on the standard dataset, achieves near state-of-the-art performance on mean rank (MR). In direct contrast to current complex and over-parametrised architectures that are both compute and time intensive, our method ignores the visual stimuli, ignores the sequencing of dialogue, does not need gradients, uses off-the-shelf feature extractors, has at least an order of magnitude fewer parameters, and learns in practically no time. We argue that these results are indicative of issues in current approaches to Visual Dialogue and conduct analyses to highlight implicit dataset biases and effects of over-constrained evaluation metrics. Our code is publicly available.

## 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/1812.06417>)

[PDF](<https://arxiv.org/pdf/1812.06417.pdf>)
