What Time Tells Us? Time-Aware Representation Learning from Static Images

Dongheng Lin, Han Hu, Jianbo Jiao

Keywords: Representation Learning, Dataset, Cross-modal, Time

TL;DR: In this paper, we try to answer What Time Tells Us by studying time-aware representation learning from static images.

Abstract: Time becomes visible through changes in what we see, as daylight fades and shadows grow. Inspired by this, in this paper we explore the potential to learn time-aware representations 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 timestamp and related visual representations through cross-modal contrastive learning. We found that the proposed TICL, 1) not only achieve state-of-the-art performance on the timestamp estimation task, over various benchmark metrics, 2) but also, interestingly, though only seeing static images, the representations learned by 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 confirm that time-aware visual representations are learnable from static images and beneficial for various vision tasks, laying a foundation for future research on understanding time-related visual context.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5403