# Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories

arXiv: https://arxiv.org/abs/2410.11657 · HTML: https://mlsanity.com/paper/2410.11657/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 54 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [Quantifying the visual concreteness of words and topics in multimodal datasets](https://mlsanity.com/paper/1804.06786/) (2018)
- [Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings](https://mlsanity.com/paper/1807.02903/) (2018)
- [Features of Perceived Metaphoricity on the Discourse Level: Abstractness and Emotionality](https://mlsanity.com/paper/2205.08939/) (2022)
- [The Scenario Refiner: Grounding subjects in images at the morphological level](https://mlsanity.com/paper/2309.11252/) (2023)
- [Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum](https://mlsanity.com/paper/2311.04563/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Computational Approach to Visual Metonymy](https://mlsanity.com/paper/2601.17706/) (2026)
- [Uncovering Visual-Semantic Psycholinguistic Properties from the Distributional Structure of Text Embedding Space](https://mlsanity.com/paper/2505.23029/) (2025)
- [Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack](https://mlsanity.com/paper/2610.00973/) (2026)

## Abstract (arXiv)

The visual representation of a concept varies significantly depending on its meaning and the context where it occurs; this poses multiple challenges both for vision and multimodal models. Our study focuses on concreteness, a well-researched lexical-semantic variable, using it as a case study to examine the variability in visual representations. We rely on images associated with approximately 1,000 abstract and concrete concepts extracted from two different datasets: Bing and YFCC. Our goals are: (i) evaluate whether visual diversity in the depiction of concepts can reliably distinguish between concrete and abstract concepts; (ii) analyze the variability of visual features across multiple images of the same concept through a nearest neighbor analysis; and (iii) identify challenging factors contributing to this variability by categorizing and annotating images. Our findings indicate that for classifying images of abstract versus concrete concepts, a combination of basic visual features such as color and texture is more effective than features extracted by more complex models like Vision Transformer (ViT). However, ViTs show better performances in the nearest neighbor analysis, emphasizing the need for a careful selection of visual features when analyzing conceptual variables through modalities other than text.