Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning

TL;DR

This paper investigates whether vision-language models can reason about the time and location of images using visual cues, revealing their strengths and limitations in commonsense reasoning tasks.

Contribution

The paper introduces a new dataset, WikiTiLo, and a two-stage probing framework to evaluate VLMs' ability to recognize and reason about temporal and spatial information.

Findings

VLMs effectively recognize relevant features in images.

VLMs still struggle with accurate reasoning about time and location.

The dataset and code are released for future research.

Abstract

Vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if, based on visual cues, Vision-Language Models that are pre-trained with large-scale image-text resources can achieve and even outperform human's capability in reasoning times and location. To address this question, we propose a two-stage \recognition\space and \reasoning\space probing task, applied to discriminative and generative VLMs to uncover whether VLMs can recognize times and location-relevant features and further reason about it. To facilitate the investigation, we introduce WikiTiLo, a well-curated image dataset compromising images with rich socio-cultural cues. In the extensive experimental studies, we find that although VLMs can effectively retain relevant features in visual encoders, they still fail to make perfect reasoning. We will release our dataset and codes to facilitate future studies.