# MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition

arXiv: https://arxiv.org/abs/2507.18929 · HTML: https://mlsanity.com/paper/2507.18929/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal emotion understanding, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Multimodal emotion understanding](https://mlsanity.com/mllm/multimodal-emotion-understanding/)

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking Spatial Dimensions of Vision Transformers](https://mlsanity.com/paper/2103.16302/) (2021)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark](https://mlsanity.com/paper/1605.02677/) (2016)
- [STICKERCONV: Generating Multimodal Empathetic Responses from Scratch](https://mlsanity.com/paper/2402.01679/) (2024)
- [MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention](https://mlsanity.com/paper/2406.05344/) (2024)
- [What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes](https://mlsanity.com/paper/2212.00715/) (2022)
- [Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models](https://mlsanity.com/paper/2401.13298/) (2024)
- [PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression](https://mlsanity.com/paper/1909.05693/) (2019)
- [Modularized Networks for Few-shot Hateful Meme Detection](https://mlsanity.com/paper/2402.11845/) (2024)
- [Multi-Granular Multimodal Clue Fusion for Meme Understanding](https://mlsanity.com/paper/2503.12560/) (2025)
- [APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation](https://mlsanity.com/paper/2407.21048/) (2024)
- [M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought](https://mlsanity.com/paper/2410.09220/) (2024)
- [Reply with Sticker: New Dataset and Model for Sticker Retrieval](https://mlsanity.com/paper/2403.05427/) (2024)

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

- [Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection](https://mlsanity.com/paper/2511.17587/) (2025)
- [GSE: Evaluating Sticker Visual Semantic Similarity via a General Sticker Encoder](https://mlsanity.com/paper/2511.04977/) (2025)
- [Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding](https://mlsanity.com/paper/2607.28659/) (2026)
- [ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation](https://mlsanity.com/paper/2608.21925/) (2026)

## Abstract (arXiv)

Although pre-trained visual models with text have demonstrated strong capabilities in visual feature extraction, sticker emotion understanding remains challenging due to its reliance on multi-view information, such as background knowledge and stylistic cues. To address this, we propose a novel multi-granularity hierarchical fusion transformer (MGHFT), with a multi-view sticker interpreter based on Multimodal Large Language Models. Specifically, inspired by the human ability to interpret sticker emotions from multiple views, we first use Multimodal Large Language Models to interpret stickers by providing rich textual context via multi-view descriptions. Then, we design a hierarchical fusion strategy to fuse the textual context into visual understanding, which builds upon a pyramid visual transformer to extract both global and local sticker features at multiple stages. Through contrastive learning and attention mechanisms, textual features are injected at different stages of the visual backbone, enhancing the fusion of global- and local-granularity visual semantics with textual guidance. Finally, we introduce a text-guided fusion attention mechanism to effectively integrate the overall multimodal features, enhancing semantic understanding. Extensive experiments on 2 public sticker emotion datasets demonstrate that MGHFT significantly outperforms existing sticker emotion recognition approaches, achieving higher accuracy and more fine-grained emotion recognition. Compared to the best pre-trained visual models, our MGHFT also obtains an obvious improvement, 5.4% on F1 and 4.0% on accuracy. The code is released at https://github.com/cccccj-03/MGHFT_ACMMM2025.