# ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception

arXiv: https://arxiv.org/abs/2604.12255 · HTML: https://mlsanity.com/paper/2604.12255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 30 of 33)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [DiffIR: Efficient Diffusion Model for Image Restoration](https://mlsanity.com/paper/2303.09472/) (2023)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [GANimation: Anatomically-aware Facial Animation from a Single Image](https://mlsanity.com/paper/1807.09251/) (2018)
- [UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content](https://mlsanity.com/paper/2005.14354/) (2020)
- [Diffusion Models for Video Prediction and Infilling](https://mlsanity.com/paper/2206.07696/) (2022)
- [DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild](https://mlsanity.com/paper/2008.05924/) (2020)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [End-to-End Diffusion Latent Optimization Improves Classifier Guidance](https://mlsanity.com/paper/2303.13703/) (2023)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [Pose Guided Human Video Generation](https://mlsanity.com/paper/1807.11152/) (2018)
- [VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2111.13579/) (2021)
- [Understanding Object Dynamics for Interactive Image-to-Video Synthesis](https://mlsanity.com/paper/2106.11303/) (2021)
- [LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content](https://mlsanity.com/paper/2403.05854/) (2024)
- [Towards Localized Fine-Grained Control for Facial Expression Generation](https://mlsanity.com/paper/2407.20175/) (2024)
- [Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data](https://mlsanity.com/paper/2409.06154/) (2024)

## Abstract (arXiv)

Dynamic facial expression recognition in the wild remains challenging due to data scarcity and long-tail distributions, which hinder models from effectively learning the temporal dynamics of scarce emotions. To address these limitations, we propose ARGen, an Affect-Reinforced Generative Augmentation Framework that enables data-adaptive dynamic expression generation for robust emotion perception. ARGen operates in two stages: Affective Semantic Injection (ASI) and Adaptive Reinforcement Diffusion (ARD). The ASI stage establishes affective knowledge alignment through facial Action Units and employs a retrieval-augmented prompt generation strategy to synthesize consistent and fine-grained affective descriptions via large-scale visual-language models, thereby injecting interpretable emotional priors into the generation process. The ARD stage integrates text-conditioned image-to-video diffusion with reinforcement learning, introducing inter-frame conditional guidance and a multi-objective reward function to jointly optimize expression naturalness, facial integrity, and generative efficiency. Extensive experiments on both generation and recognition tasks verify that ARGen substantially enhances synthesis fidelity and improves recognition performance, establishing an interpretable and generalizable generative augmentation paradigm for vision-based affective computing.