VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

• URL: http://arxiv.org/abs/2505.02331v1
• Date: Mon, 05 May 2025 03:00:51 GMT
• Title: VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection
• Abstract summary: We propose VAEmo, an efficient framework for emotion-centric joint VA representation learning with external knowledge injection.<n>VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance.
• Score: 50.57849622045192
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issues, we propose VAEmo, an efficient two-stage framework for emotion-centric joint VA representation learning with external knowledge injection. In Stage 1, a unified and lightweight representation network is pre-trained on large-scale speaker-centric VA corpora via masked reconstruction and contrastive objectives, mitigating the modality gap and learning expressive, complementary representations without emotion labels. In Stage 2, multimodal large language models automatically generate detailed affective descriptions according to our well-designed chain-of-thought prompting for only a small subset of VA samples; these rich textual semantics are then injected by aligning their corresponding embeddings with VA representations through dual-path contrastive learning, further bridging the emotion gap. Extensive experiments on multiple downstream AVER benchmarks show that VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance for efficient, generalizable VA emotion representations.

Related papers

• ViQ: Text-Aligned Visual Quantized Representations at Any Resolution [91.46185855575789]
  We present ViQ, a Visual Quantized Representations framework, which is designed to balance semantics and details in discrete representations.<n>Our approach structures quantization learning into two stages: text-aligned pre-training and feature discretization.<n>Experiments on multimodal tasks demonstrate that ViQ achieves competitive performance compared to state-of-the-art multimodal vision encoders.
  arXiv  Detail & Related papers  (2026-06-25T17:29:27Z)
• VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation [17.099995082943735]
  Emotion Recognition in Conversation (ERC) is essential for effective human-machine interaction.<n>Recent Vision-Language Models (VLMs) are not inherently tailored for ERC.<n>We propose VISAFF, a speaker-centered VISual AFFective feature learning framework for ERC.
  arXiv  Detail & Related papers  (2026-05-18T15:27:10Z)
• Disentangled Dual-Branch Graph Learning for Conversational Emotion Recognition [37.30058027224552]
  Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context.<n>We propose a framework that combines dual-space feature disentanglement with dual-branch graph learning.<n> Experiments on IEMOCAP and MELD demonstrate that the proposed method achieves superior performance over strong baselines.
  arXiv  Detail & Related papers  (2026-04-03T14:47:26Z)
• Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling [2.8037951156321377]
  We propose a multimodal emotion recognition framework for the Expression task in the 10th Affective Behavior Analysis in-the-wild (ABAW) Challenge.<n>Our framework builds on large-scale pre-trained models for visual and audio representation learning and integrates them in a unified multimodal architecture.<n> Experimental results on the ABAW 10th EXPR benchmark demonstrate the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2026-03-12T14:20:29Z)
• ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning [67.22219034602514]
  We introduce ADEPT (Agentic Decoding of Emotion via Evidence Probing Tools), a framework that reframes emotion recognition as a multi-turn inquiry process.<n> ADEPT transforms an SLLM into an agent that maintains an evolving candidate emotion set and adaptively invokes dedicated semantic and acoustic probing tools.<n>We show that ADEPT improves primary emotion accuracy in most settings while substantially improving minor emotion characterization.
  arXiv  Detail & Related papers  (2026-02-13T08:33:37Z)
• EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis [61.87711517626139]
  EmoVerse is a large-scale open-source dataset that enables interpretable visual emotion analysis.<n>With over 219k images, the dataset further includes dual annotations in Categorical Emotion States (CES) and Dimensional Emotion Space (DES)
  arXiv  Detail & Related papers  (2025-11-16T11:16:50Z)
• Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound [21.4061944104446]
  Art conveys emotion through the joint design of visual and auditory elements, yet most prior work is human-centered or single-modality.<n>We present Vision Anchored Audio-Visual Emotion LLM (VAEmotionLLM), a two-stage framework that teaches a VLM to hear by seeing with limited audio pretraining.<n>VAEmotionLLM achieves state-of-the-art results on ArtEmoBenchmark, outperforming audio-only, visual-only, and audio-visual baselines.
  arXiv  Detail & Related papers  (2025-11-15T07:42:02Z)
• Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition [7.243987016933212]
  This paper introduces a two-step approach to enhance robustness and generalization of speech emotion recognition models.<n> improved performance under challenging conditions demonstrates the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2025-10-10T07:17:07Z)
• From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition [7.362433184546492]
  Dynamic Facial Expression Recognition aims to identify human emotions from temporally evolving facial movements.<n>Our method integrates dynamic motion modeling, semantic text refinement, and token-level cross-modal alignment to facilitate the precise localization of emotionally salient features.
  arXiv  Detail & Related papers  (2025-07-16T04:15:06Z)
• Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation [58.189703277322224]
  Speech-preserving facial expression manipulation (SPFEM) aims to modify a talking head to display a specific reference emotion.<n>Emotion and content information existing in reference and source inputs can provide direct and accurate supervision signals for SPFEM models.<n>We propose to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation.
  arXiv  Detail & Related papers  (2025-04-08T04:34:38Z)
• MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network [6.304608172789466]
  The proposed Multi-modal Attention for Valence-Arousal Emotion Network (MAVEN) integrates visual, audio, and textual modalities.<n>MAVEN uses modality-specific encoders to extract features from synchronized video frames, audio segments, and transcripts.<n>The architecture captures the subtle and transient nature of emotional expressions in conversational videos and improves emotion recognition in real-world situations.
  arXiv  Detail & Related papers  (2025-03-16T19:32:32Z)
• 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)
• Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion [81.1492897350032]
  Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. We propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion.
  arXiv  Detail & Related papers  (2023-12-29T08:06:45Z)
• Disentangled Variational Autoencoder for Emotion Recognition in Conversations [14.92924920489251]
  We propose a VAD-disentangled Variational AutoEncoder (VAD-VAE) for Emotion Recognition in Conversations (ERC) VAD-VAE disentangles three affect representations Valence-Arousal-Dominance (VAD) from the latent space. Experiments show that VAD-VAE outperforms the state-of-the-art model on two datasets.
  arXiv  Detail & Related papers  (2023-05-23T13:50:06Z)
• Disentangling Prosody Representations with Unsupervised Speech Reconstruction [22.873286925385543]
  The aim of this paper is to address the disentanglement of emotional prosody from speech based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed speech reconstruction model Prosody2Vec. We first pretrain the Prosody2Vec representations on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks.
  arXiv  Detail & Related papers  (2022-12-14T01:37:35Z)
• VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition [21.247650660908484]
  This paper proposes a multimodal emotion recognition system, VIsual Textual Additive Net (VISTANet) The VISTANet fuses information from image, speech, and text modalities using a hybrid of early and late fusion. The KAAP technique computes the contribution of each modality and corresponding features toward predicting a particular emotion class.
  arXiv  Detail & Related papers  (2022-08-24T11:35:51Z)
• MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition [118.73025093045652]
  We propose a pre-training model textbfMEmoBERT for multimodal emotion recognition. Unlike the conventional "pre-train, finetune" paradigm, we propose a prompt-based method that reformulates the downstream emotion classification task as a masked text prediction. Our proposed MEmoBERT significantly enhances emotion recognition performance.
  arXiv  Detail & Related papers  (2021-10-27T09:57:00Z)
• Multimodal Emotion Recognition with High-level Speech and Text Features [8.141157362639182]
  We propose a novel cross-representation speech model to perform emotion recognition on wav2vec 2.0 speech features. We also train a CNN-based model to recognize emotions from text features extracted with Transformer-based models. Our method is evaluated on the IEMOCAP dataset in a 4-class classification problem.
  arXiv  Detail & Related papers  (2021-09-29T07:08:40Z)
• An Attribute-Aligned Strategy for Learning Speech Representation [57.891727280493015]
  We propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes. Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV.
  arXiv  Detail & Related papers  (2021-06-05T06:19:14Z)

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.