Saved in:
Bibliographic Details
Main Authors: Tekaya, Nidham, Waldner, Manuela, Zeppelzauer, Matthias
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.19559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915569967562752
author Tekaya, Nidham
Waldner, Manuela
Zeppelzauer, Matthias
author_facet Tekaya, Nidham
Waldner, Manuela
Zeppelzauer, Matthias
contents Large-scale vision-language models (VLMs) such as CLIP have gained popularity for their generalizable and expressive multimodal representations. By leveraging large-scale training data with diverse textual metadata, VLMs acquire open-vocabulary capabilities, solving tasks beyond their training scope. This paper investigates the temporal awareness of VLMs, assessing their ability to position visual content in time. We introduce TIME10k, a benchmark dataset of over 10,000 images with temporal ground truth, and evaluate the time-awareness of 37 VLMs by a novel methodology. Our investigation reveals that temporal information is structured along a low-dimensional, non-linear manifold in the VLM embedding space. Based on this insight, we propose methods to derive an explicit ``timeline'' representation from the embedding space. These representations model time and its chronological progression and thereby facilitate temporal reasoning tasks. Our timeline approaches achieve competitive to superior accuracy compared to a prompt-based baseline while being computationally efficient. All code and data are available at https://tekayanidham.github.io/timeline-page/.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Matter of Time: Revealing the Structure of Time in Vision-Language Models
Tekaya, Nidham
Waldner, Manuela
Zeppelzauer, Matthias
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Multimedia
Large-scale vision-language models (VLMs) such as CLIP have gained popularity for their generalizable and expressive multimodal representations. By leveraging large-scale training data with diverse textual metadata, VLMs acquire open-vocabulary capabilities, solving tasks beyond their training scope. This paper investigates the temporal awareness of VLMs, assessing their ability to position visual content in time. We introduce TIME10k, a benchmark dataset of over 10,000 images with temporal ground truth, and evaluate the time-awareness of 37 VLMs by a novel methodology. Our investigation reveals that temporal information is structured along a low-dimensional, non-linear manifold in the VLM embedding space. Based on this insight, we propose methods to derive an explicit ``timeline'' representation from the embedding space. These representations model time and its chronological progression and thereby facilitate temporal reasoning tasks. Our timeline approaches achieve competitive to superior accuracy compared to a prompt-based baseline while being computationally efficient. All code and data are available at https://tekayanidham.github.io/timeline-page/.
title A Matter of Time: Revealing the Structure of Time in Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Multimedia
url https://arxiv.org/abs/2510.19559