Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding

• URL: http://arxiv.org/abs/2505.06685v2
• Date: Fri, 30 May 2025 12:27:30 GMT
• Title: Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding
• Authors: Dawei Huang, Qing Li, Chuan Yan, Zebang Cheng, Yurong Huang, Xiang Li, Bin Li, Xiaohui Wang, Zheng Lian, Xiaojiang Peng,
• Abstract summary: We present Emotion-Qwen, a tailored framework designed to enhance both emotion understanding and general vision-language reasoning.<n>Emotion-Qwen incorporates a sophisticated Hybrid based on the Mixture of Experts (MoE) paradigm, which dynamically routes inputs to balance emotion-specific and general-purpose processing.<n>We construct the Video Emotion Reasoning (VER) dataset, comprising more than 40K bilingual video clips with fine-grained descriptive annotations, to further enrich Emotion-Qwen's emotional reasoning capability.
• Score: 24.884935271771624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emotion understanding in videos aims to accurately recognize and interpret individuals' emotional states by integrating contextual, visual, textual, and auditory cues. While Large Multimodal Models (LMMs) have demonstrated significant progress in general vision-language (VL) tasks, their performance in emotion-specific scenarios remains limited. Moreover, fine-tuning LMMs on emotion-related tasks often leads to catastrophic forgetting, hindering their ability to generalize across diverse tasks. To address these challenges, we present Emotion-Qwen, a tailored multimodal framework designed to enhance both emotion understanding and general VL reasoning. Emotion-Qwen incorporates a sophisticated Hybrid Compressor based on the Mixture of Experts (MoE) paradigm, which dynamically routes inputs to balance emotion-specific and general-purpose processing. The model is pre-trained in a three-stage pipeline on large-scale general and emotional image datasets to support robust multimodal representations. Furthermore, we construct the Video Emotion Reasoning (VER) dataset, comprising more than 40K bilingual video clips with fine-grained descriptive annotations, to further enrich Emotion-Qwen's emotional reasoning capability. Experimental results demonstrate that Emotion-Qwen achieves state-of-the-art performance on multiple emotion recognition benchmarks, while maintaining competitive results on general VL tasks. Code and models are available at https://github.com/24DavidHuang/Emotion-Qwen.

Related papers

• UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries [61.5273479616832]
  We propose a unified framework that seamlessly integrates emotional understanding and generation.<n>We show that UniEmo significantly outperforms state-of-the-art methods in both emotional understanding and generation tasks.
  arXiv  Detail & Related papers  (2025-07-31T09:39:27Z)
• Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation [63.94836524433559]
  DICE-Talk is a framework for disentangling identity with emotion and cooperating emotions with similar characteristics.<n>We develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention.<n>Second, we introduce a correlation-enhanced emotion conditioning module with learnable Emotion Banks.<n>Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process.
  arXiv  Detail & Related papers  (2025-04-25T05:28:21Z)
• AI with Emotions: Exploring Emotional Expressions in Large Language Models [0.0]
  Large Language Models (LLMs) play role-play as agents answering questions with specified emotional states.<n>Russell's Circumplex model characterizes emotions along the sleepy-activated (arousal) and pleasure-displeasure (valence) axes.<n> evaluation showed that the emotional states of the generated answers were consistent with the specifications.
  arXiv  Detail & Related papers  (2025-04-20T18:49:25Z)
• Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis [6.387263468033964]
  We introduce a self-reviewed dataset and a human-reviewed dataset, comprising 24,137 coarse-grained samples and 3,500 manually annotated samples with detailed emotion annotations.<n>In addition to the audio modeling, we propose to explicitly integrate facial encoding models into the existing advanced Video MLLM.<n>Our Omni-Emotion achieves state-of-the-art performance in both emotion recognition and reasoning tasks.
  arXiv  Detail & Related papers  (2025-01-16T12:27:05Z)
• MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation [39.30784838378127]
  The generation of talking avatars has achieved significant advancements in precise audio synchronization.<n>Current methods face fundamental challenges, including the lack of frameworks for modeling single basic emotional expressions.<n>We propose the Mixture of Emotion Experts (MoEE) model, which decouples six fundamental emotions to enable the precise synthesis of both singular and compound emotional states.<n>In conjunction with the DH-FaceEmoVid-150 dataset, we demonstrate that the MoEE framework excels in generating complex emotional expressions and nuanced facial details.
  arXiv  Detail & Related papers  (2025-01-03T13:43:21Z)
• Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content [56.62027582702816]
  Multimodal Sentiment Analysis seeks to unravel human emotions by amalgamating text, audio, and visual data.<n>Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge.<n>We introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions.
  arXiv  Detail & Related papers  (2024-12-12T11:30:41Z)
• EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding [5.3848462080869215]
  We introduce Emotion Universe (EmoVerse), an MLLM designed to handle a broad spectrum of sentiment and emotion-related tasks.<n>EmoVerse is capable of deeply analyzing the underlying causes of emotional states.<n>We also introduce the Affective Multitask (AMT) dataset.
  arXiv  Detail & Related papers  (2024-12-11T02:55:00Z)
• When Words Smile: Generating Diverse Emotional Facial Expressions from Text [72.19705878257204]
  We introduce an end-to-end text-to-expression model that explicitly focuses on emotional dynamics.<n>Our model learns expressive facial variations in a continuous latent space and generates expressions that are diverse, fluid, and emotionally coherent.
  arXiv  Detail & Related papers  (2024-12-03T15:39:05Z)
• EmoLLM: Multimodal Emotional Understanding Meets Large Language Models [61.179731667080326]
  Multi-modal large language models (MLLMs) have achieved remarkable performance on objective multimodal perception tasks. But their ability to interpret subjective, emotionally nuanced multimodal content remains largely unexplored. EmoLLM is a novel model for multimodal emotional understanding, incorporating with two core techniques.
  arXiv  Detail & Related papers  (2024-06-24T08:33:02Z)
• Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought [50.13429055093534]
  Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks. We propose the Emotional Chain-of-Thought (ECoT) to enhance the performance of LLMs on various emotional generation tasks.
  arXiv  Detail & Related papers  (2024-01-12T16:42:10Z)
• Stimuli-Aware Visual Emotion Analysis [75.68305830514007]
  We propose a stimuli-aware visual emotion analysis (VEA) method consisting of three stages, namely stimuli selection, feature extraction and emotion prediction. To the best of our knowledge, it is the first time to introduce stimuli selection process into VEA in an end-to-end network. Experiments demonstrate that the proposed method consistently outperforms the state-of-the-art approaches on four public visual emotion datasets.
  arXiv  Detail & Related papers  (2021-09-04T08:14:52Z)
• Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies [106.62835060095532]
  We discuss several key aspects of multi-modal emotion recognition (MER) We begin with a brief introduction on widely used emotion representation models and affective modalities. We then summarize existing emotion annotation strategies and corresponding computational tasks. Finally, we outline several real-world applications and discuss some future directions.
  arXiv  Detail & Related papers  (2021-08-18T21:55:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.