# Supervised mid-level features for word image representation

arXiv: https://arxiv.org/abs/1410.5224 · HTML: https://mlsanity.com/paper/1410.5224/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2014.

## Built on by (most cited first, 5 of 5)

- [Learning Super-Features for Image Retrieval](https://mlsanity.com/paper/2201.13182/) (2022)
- [Convolutional Neural Networks with Gated Recurrent Connections](https://mlsanity.com/paper/2106.02859/) (2021)
- [Vision Transformer attention alignment with human visual perception in aesthetic object evaluation](https://mlsanity.com/paper/2507.17616/) (2025)
- [Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal](https://mlsanity.com/paper/2410.08332/) (2024)
- [Scene Text recognition with Full Normalization](https://mlsanity.com/paper/2109.01034/) (2021)

## Abstract (arXiv)

This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be supplied with these representations to produce models useful for word retrieval or recognition tasks. Although many works have focused on the machine learning aspect once a global representation has been produced, little work has been devoted to the construction of those base image representations: most works use standard coding and aggregation techniques directly on top of standard computer vision features such as SIFT or HOG. We propose to learn local mid-level features suitable for building word image representations. These features are learnt by leveraging character bounding box annotations on a small set of training images. However, contrary to other approaches that use character bounding box information, our approach does not rely on detecting the individual characters explicitly at testing time. Our local mid-level features can then be aggregated to produce a global word image signature. When pairing these features with the recent word attributes framework of Almaz'an et al., we obtain results comparable with or better than the state-of-the-art on matching and recognition tasks using global descriptors of only 96 dimensions.