It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Jaeha, Lee, Jin Won, You, Siwoo, Lee, Jangho
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914595949510656
author Choi, Jaeha
Lee, Jin Won
You, Siwoo
Lee, Jangho
author_facet Choi, Jaeha
Lee, Jin Won
You, Siwoo
Lee, Jangho
contents Advances in vision-language models (VLMs) have achieved remarkable success on complex multimodal reasoning tasks, leading to the assumption that they should also excel at reading analog clocks. However, contrary to this expectation, our study reveals that reading analog clocks in real-world environments remains a significant challenge for state-of-the-art VLMs. Existing analog clock datasets are largely synthetic or planar with limited stylistic diversity and minimal background context, failing to capture the visual variability of real-world scenes. As a result, VLMs trained on such data exhibit weak spatiotemporal reasoning, frequently confusing the hour and minute hands and struggling under common visual conditions such as occlusion, lighting variation, and cluttered backgrounds. To address this issue, we introduce TickTockVQA, a human-annotated dataset containing analog clocks in diverse real-world scenarios. TickTockVQA provides explicit hour and minute annotations, and includes an AM/PM tag when it is inferable from the visual context. Furthermore, we propose Swap-DPO, a direct preference optimization-based fine-tuning framework to align model reasoning toward accurate time interpretation. Experimental results demonstrate that our approach substantially enhances clock reading accuracy and robustness under real-world conditions, establishing a foundation for future research on spatiotemporal reasoning and visual understanding in VLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models
Choi, Jaeha
Lee, Jin Won
You, Siwoo
Lee, Jangho
Computer Vision and Pattern Recognition
Advances in vision-language models (VLMs) have achieved remarkable success on complex multimodal reasoning tasks, leading to the assumption that they should also excel at reading analog clocks. However, contrary to this expectation, our study reveals that reading analog clocks in real-world environments remains a significant challenge for state-of-the-art VLMs. Existing analog clock datasets are largely synthetic or planar with limited stylistic diversity and minimal background context, failing to capture the visual variability of real-world scenes. As a result, VLMs trained on such data exhibit weak spatiotemporal reasoning, frequently confusing the hour and minute hands and struggling under common visual conditions such as occlusion, lighting variation, and cluttered backgrounds. To address this issue, we introduce TickTockVQA, a human-annotated dataset containing analog clocks in diverse real-world scenarios. TickTockVQA provides explicit hour and minute annotations, and includes an AM/PM tag when it is inferable from the visual context. Furthermore, we propose Swap-DPO, a direct preference optimization-based fine-tuning framework to align model reasoning toward accurate time interpretation. Experimental results demonstrate that our approach substantially enhances clock reading accuracy and robustness under real-world conditions, establishing a foundation for future research on spatiotemporal reasoning and visual understanding in VLMs.
title It's Time to Get It Right: Improving Analog Clock Reading and Clock-Hand Spatial Reasoning in Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.08011