There is a Time and Place for Reasoning Beyond the Image

TL;DR

This paper introduces TARA, a dataset and model for reasoning about the time and place of images using contextual information, demonstrating a significant gap between current models and human performance.

Contribution

The work presents a new dataset, TARA, with 16k images and associated spatio-temporal data, and proposes a model that improves reasoning about image context beyond state-of-the-art methods.

Findings

70% gap between model and human performance

Segment-wise reasoning improves accuracy

Dataset enables research on open-ended reasoning

Abstract

Images are often more significant than only the pixels to human eyes, as we can infer, associate, and reason with contextual information from other sources to establish a more complete picture. For example, in Figure 1, we can find a way to identify the news articles related to the picture through segment-wise understandings of the signs, the buildings, the crowds, and more. This reasoning could provide the time and place the image was taken, which will help us in subsequent tasks, such as automatic storyline construction, correction of image source in intended effect photographs, and upper-stream processing such as image clustering for certain location or time. In this work, we formulate this problem and introduce TARA: a dataset with 16k images with their associated news, time, and location, automatically extracted from New York Times, and an additional 61k examples as distant supervision from WIT. On top of the extractions, we present a crowdsourced subset in which we believe it is possible to find the images' spatio-temporal information for evaluation purpose. We show that there exists a $70\%$ gap between a state-of-the-art joint model and human performance, which is slightly filled by our proposed model that uses segment-wise reasoning, motivating higher-level vision-language joint models that can conduct open-ended reasoning with world knowledge. The data and code are publicly available at https://github.com/zeyofu/TARA.