Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling

• URL: http://arxiv.org/abs/2603.11971v1
• Date: Thu, 12 Mar 2026 14:20:29 GMT
• Title: Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling
• Abstract summary: We propose a multimodal emotion recognition framework for the Expression (EXPR) Recognition task in the 10th Affective Behavior Analysis in-the-wild (ABAW) Challenge.<n>To model temporal dependencies in facial expression sequences, we employ a Temporal Convolutional Network (TCN) over fixed-length video windows.<n>In addition, we introduce a bi-directional cross-attention fusion module, in which visual and audio features interact symmetrically to enhance cross-modal contextualization.
• Score: 2.8037951156321377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emotion recognition in in-the-wild video data remains a challenging problem due to large variations in facial appearance, head pose, illumination, background noise, and the inherently dynamic nature of human affect. Relying on a single modality, such as facial expressions or speech, is often insufficient to capture these complex emotional cues. To address this issue, we propose a multimodal emotion recognition framework for the Expression (EXPR) Recognition task in the 10th Affective Behavior Analysis in-the-wild (ABAW) Challenge. Our approach leverages large-scale pre-trained models, namely CLIP for visual encoding and Wav2Vec 2.0 for audio representation learning, as frozen backbone networks. To model temporal dependencies in facial expression sequences, we employ a Temporal Convolutional Network (TCN) over fixed-length video windows. In addition, we introduce a bi-directional cross-attention fusion module, in which visual and audio features interact symmetrically to enhance cross-modal contextualization and capture complementary emotional information. A lightweight classification head is then used for final emotion prediction. We further incorporate a text-guided contrastive objective based on CLIP text features to encourage semantically aligned visual representations. Experimental results on the ABAW 10th EXPR benchmark show that the proposed framework provides a strong multimodal baseline and achieves improved performance over unimodal modeling. These results demonstrate the effectiveness of combining temporal visual modeling, audio representation learning, and cross-modal fusion for robust emotion recognition in unconstrained real-world environments.

Related papers

• Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis [36.79172273160707]
  Facial expressions encode subtle and rich affective cues that are crucial for empathetic speech interaction.<n>We propose FacialTalker, a facial-expression-aware CSS framework built upon a large language model backbone.<n>We construct VSDD-1K, a large-scale multimodal dialogue dataset collected through a fully automated pipeline from real-world Internet conversations.
  arXiv  Detail & Related papers  (2026-07-27T13:42:37Z)
• Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation [63.90351637818903]
  Speech-preserving facial expression manipulation aims to enhance human expressiveness without altering mouth movements tied to the original speech.<n>Current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision.<n>We propose a Personalized Cross-Modal Emotional Correlation Learning algorithm that refines VLM-based supervision.
  arXiv  Detail & Related papers  (2026-04-28T06:02:23Z)
• AMB-DSGDN: Adaptive Modality-Balanced Dynamic Semantic Graph Differential Network for Multimodal Emotion Recognition [35.370240758006936]
  Multimodal dialogue emotion recognition captures emotional cues by fusing text, visual, and audio modalities.<n>Existing approaches still suffer from notable limitations in modeling emotional dependencies and learning multimodal representations.<n>We propose an Adaptive Modality-Balanced Dynamic Semantic Graph Differential Network (AMB-DSGDN)
  arXiv  Detail & Related papers  (2026-03-07T11:23:23Z)
• MIBURI: Towards Expressive Interactive Gesture Synthesis [62.45332399212876]
  Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions.<n>Existing solutions for ECAs produce rigid, low-diversity motions that are unsuitable for human-like interaction.<n>We present MIBURI, the first online, causal framework for generating expressive full-body gestures and facial expressions synchronized with real-time spoken dialogue.
  arXiv  Detail & Related papers  (2026-03-03T18:59:51Z)
• Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition [49.41688891301643]
  Dynamic facial expression recognition aims to identify emotional states by modeling the temporal changes in facial movements across video sequences.<n>A key challenge in DFER is the many-to-one labeling problem, where a video composed of numerous frames is assigned a single emotion label.<n>We propose TG-DFER, a text-guided weakly supervised framework that enhances MIL-based DFER by incorporating semantic guidance and coherent temporal modeling.
  arXiv  Detail & Related papers  (2025-11-14T04:49:58Z)
• Beyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues [13.756325086005369]
  Desire, as an intention that drives human behavior, is closely related to both emotion and sentiment.<n>We propose a Symmetrical Bimodal Multimodal Learning Framework for Desire, Emotion, and Sentiment Recognition.<n>Low-resolution images are used to obtain global visual representations for cross-modal alignment.<n>High-resolution images are partitioned into sub-images and modeled with masked image modeling.
  arXiv  Detail & Related papers  (2025-09-19T02:49:47Z)
• EmoCAST: Emotional Talking Portrait via Emotive Text Description [56.42674612728354]
  EmoCAST is a diffusion-based framework for precise text-driven emotional synthesis.<n>In appearance modeling, emotional prompts are integrated through a text-guided decoupled emotive module.<n>EmoCAST achieves state-of-the-art performance in generating realistic, emotionally expressive, and audio-synchronized talking-head videos.
  arXiv  Detail & Related papers  (2025-08-28T10:02:06Z)
• 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)
• VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection [50.57849622045192]
  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.
  arXiv  Detail & Related papers  (2025-05-05T03:00:51Z)
• 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)
• HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition [16.860963320038902]
  This article presents our results for the eighth Affective Behavior Analysis in-the-Wild (ABAW) competition.<n>We combine facial emotional descriptors extracted by pre-trained models with acoustic features and embeddings of texts recognized from speech.<n>The video-level prediction of emotional mimicry intensity is implemented by simply aggregating frame-level features and training a multi-layered perceptron.
  arXiv  Detail & Related papers  (2025-03-13T14:21:46Z)
• 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)
• When Words Smile: Generating Diverse Emotional Facial Expressions from Text [77.1867389815291]
  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)
• EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion [49.55774551366049]
  Diffusion models have revolutionized the field of talking head generation, yet still face challenges in expressiveness, controllability, and stability in long-time generation.<n>We propose an EmotiveTalk framework to address these issues.<n> Experimental results show that EmotiveTalk can generate expressive talking head videos, ensuring the promised controllability of emotions and stability during long-time generation.
  arXiv  Detail & Related papers  (2024-11-23T04:38:51Z)
• Joint Multimodal Transformer for Emotion Recognition in the Wild [49.735299182004404]
  Multimodal emotion recognition (MMER) systems typically outperform unimodal systems. This paper proposes an MMER method that relies on a joint multimodal transformer (JMT) for fusion with key-based cross-attention.
  arXiv  Detail & Related papers  (2024-03-15T17:23:38Z)
• AMuSE: Adaptive Multimodal Analysis for Speaker Emotion Recognition in Group Conversations [39.79734528362605]
  Multimodal Attention Network captures cross-modal interactions at various levels of spatial abstraction. AMuSE model condenses both spatial and temporal features into two dense descriptors: speaker-level and utterance-level.
  arXiv  Detail & Related papers  (2024-01-26T19:17:05Z)
• Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models [53.31917090073727]
  We propose a neural network-based emotion recognition framework that uses a late fusion of transfer-learned and fine-tuned models from speech and text modalities. We evaluate the effectiveness of our proposed multimodal approach on the interactive emotional dyadic motion capture dataset.
  arXiv  Detail & Related papers  (2022-02-16T00:23:42Z)
• Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild [31.40575057347465]
  We tackle the task of video-based visual emotion recognition in the wild. Standard methodologies that rely solely on the extraction of bodily and facial features often fall short of accurate emotion prediction. We aspire to alleviate this problem by leveraging visual context in the form of scene characteristics and attributes.
  arXiv  Detail & Related papers  (2021-05-16T17:31:59Z)

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.