# It's About Time: Analog Clock Reading in the Wild

arXiv: https://arxiv.org/abs/2111.09162 · HTML: https://mlsanity.com/paper/2111.09162/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 17 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://mlsanity.com/paper/1908.08207/) (2019)
- [ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network](https://mlsanity.com/paper/2002.10200/) (2020)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [FOTS: Fast Oriented Text Spotting with a Unified Network](https://mlsanity.com/paper/1801.01671/) (2018)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Sim2real transfer learning for 3D human pose estimation: motion to the rescue](https://mlsanity.com/paper/1907.02499/) (2019)
- [Towards Unconstrained End-to-End Text Spotting](https://mlsanity.com/paper/1908.09231/) (2019)
- [Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach](https://mlsanity.com/paper/2009.10181/) (2020)
- [Deep Learning for Image-based Automatic Dial Meter Reading: Dataset and Baselines](https://mlsanity.com/paper/2005.03106/) (2020)

## Built on by (most cited first, 14 of 14)

- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model](https://mlsanity.com/paper/2503.13026/) (2025)
- [M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance](https://mlsanity.com/paper/2502.18778/) (2025)
- [Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs](https://mlsanity.com/paper/2502.05092/) (2025)
- [Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench](https://mlsanity.com/paper/2510.26865/) (2025)
- [Made to Order: Discovering monotonic temporal changes via self-supervised video ordering](https://mlsanity.com/paper/2404.16828/) (2024)
- [Image-based Automatic Dial Meter Reading in Unconstrained Scenarios](https://mlsanity.com/paper/2201.02850/) (2022)
- [Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2308.03097/) (2023)
- [ZAYA1-VL-8B Technical Report](https://mlsanity.com/paper/2605.08560/) (2026)
- [Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm](https://mlsanity.com/paper/2302.14323/) (2023)
- [State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading](https://mlsanity.com/paper/2604.26614/) (2026)
- [Zamba2-VL Technical Report](https://mlsanity.com/paper/2606.00390/) (2026)
- [It's Always 10:10: Reference Images Break a Bias That Prompts Only Dent](https://mlsanity.com/paper/2610.11320/) (2026)

## Abstract (arXiv)

In this paper, we present a framework for reading analog clocks in natural images or videos. Specifically, we make the following contributions: First, we create a scalable pipeline for generating synthetic clocks, significantly reducing the requirements for the labour-intensive annotations; Second, we introduce a clock recognition architecture based on spatial transformer networks (STN), which is trained end-to-end for clock alignment and recognition. We show that the model trained on the proposed synthetic dataset generalises towards real clocks with good accuracy, advocating a Sim2Real training regime; Third, to further reduce the gap between simulation and real data, we leverage the special property of "time", i.e.uniformity, to generate reliable pseudo-labels on real unlabelled clock videos, and show that training on these videos offers further improvements while still requiring zero manual annotations. Lastly, we introduce three benchmark datasets based on COCO, Open Images, and The Clock movie, with full annotations for time, accurate to the minute.