# Disturbing Image Detection Using LMM-Elicited Emotion Embeddings

arXiv: https://arxiv.org/abs/2406.12668 · HTML: https://mlsanity.com/paper/2406.12668/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models](https://mlsanity.com/paper/2212.00668/) (2022)
- [Exploiting LMM-based knowledge for image classification tasks](https://mlsanity.com/paper/2406.03071/) (2024)
- [Mitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study](https://mlsanity.com/paper/2307.10334/) (2023)

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

- [Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge](https://mlsanity.com/paper/2504.09914/) (2025)
- [LMM-Regularized CLIP Embeddings for Image Classification](https://mlsanity.com/paper/2412.11663/) (2024)
- [Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition](https://mlsanity.com/paper/2509.04480/) (2025)
- [Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection](https://mlsanity.com/paper/2605.10394/) (2026)

## Abstract (arXiv)

In this paper we deal with the task of Disturbing Image Detection (DID), exploiting knowledge encoded in Large Multimodal Models (LMMs). Specifically, we propose to exploit LMM knowledge in a two-fold manner: first by extracting generic semantic descriptions, and second by extracting elicited emotions. Subsequently, we use the CLIP's text encoder in order to obtain the text embeddings of both the generic semantic descriptions and LMM-elicited emotions. Finally, we use the aforementioned text embeddings along with the corresponding CLIP's image embeddings for performing the DID task. The proposed method significantly improves the baseline classification accuracy, achieving state-of-the-art performance on the augmented Disturbing Image Detection dataset.