Abstract
Time becomes visible through illumination changes in what we see. Inspired by this, in this paper we explore the potential to learn time awareness from static images, trying to answer: what time tells us? To this end, we first introduce a Time-Oriented Collection (TOC) dataset, which contains 130,906 images with reliable timestamps. Leveraging this dataset, we propose a Time-Image Contrastive Learning (TICL) approach to jointly model timestamps and related visual representations through cross-modal contrastive learning. We found that the proposed TICL, 1) not only achieves state-of-the-art performance on the timestamp estimation task, over various benchmark metrics, 2) but also, interestingly, though only seeing static images, the time-aware embeddings learned from TICL show strong capability in several time-aware downstream tasks such as time-based image retrieval, video scene classification, and time-aware image editing. Our findings suggest that time-related visual cues can be learned from static images and are beneficial for various vision tasks, laying a foundation for future research on understanding time-related visual context. Project page:this https URL.
Abstract (translated)
时间通过我们所见事物的照明变化而变得可见。受此启发，本文探讨了从静态图像中学习时间感知的潜力，并尝试回答：“时间告诉我们什么？”为此，我们首先引入了一个以时间为方向的数据集（Time-Oriented Collection，简称TOC），该数据集中包含130,906张带有可靠时间戳的照片。利用这一数据集，我们提出了一种时间-图像对比学习（Time-Image Contrastive Learning，简称TICL）方法，通过跨模态对比学习共同建模时间戳及其相关的视觉表示形式。我们发现，所提出的TICL方法不仅在时间戳估计任务上实现了最先进的性能，而且令人惊讶的是，在仅接触静态图像的情况下，从TICL中学习到的时间感知嵌入在时间感知下游任务（如基于时间的图片检索、视频场景分类和具有时间意识的图片编辑）方面表现出很强的能力。我们的发现表明，可以从静态图像中学习与时间相关的视觉线索，并且这对各种视觉任务有益，为未来研究理解与时间相关的情境奠定了基础。项目页面：[此链接](https://此链接/)。
URL
https://arxiv.org/abs/2503.17899
