# Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning

arXiv: https://arxiv.org/abs/2010.02959 · HTML: https://mlsanity.com/paper/2010.02959/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Zero-Shot Robustification of Zero-Shot Models](https://mlsanity.com/paper/2309.04344/) (2023)
- [Zero-Shot Action Recognition from Diverse Object-Scene Compositions](https://mlsanity.com/paper/2110.13479/) (2021)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)

## Abstract (arXiv)

Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations. These class representations usually consist of either attributes, which do not scale well to large datasets, or word embeddings, which lead to poorer performance. A good trade-off could be to employ short sentences in natural language as class descriptions. We explore different solutions to use such short descriptions in a ZSL setting and show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art.