Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

• URL: http://arxiv.org/abs/2406.11161v2
• Date: Sat, 02 Nov 2024 02:30:50 GMT
• Title: Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
• Authors: Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, Alexander Hauptmann,
• Abstract summary: We introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. We propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders.
• Score: 55.127202990679976
• License:
• Abstract: Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. Furthermore, we propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders. By aligning features into a shared space and employing a modified LLaMA model with instruction tuning, Emotion-LLaMA significantly enhances both emotional recognition and reasoning capabilities. Extensive evaluations show Emotion-LLaMA outperforms other MLLMs, achieving top scores in Clue Overlap (7.83) and Label Overlap (6.25) on EMER, an F1 score of 0.9036 on MER2023-SEMI challenge, and the highest UAR (45.59) and WAR (59.37) in zero-shot evaluations on DFEW dataset.

Related papers

• Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model [5.301672905886949]
  This report introduces the solution of using MLLMs technology to generate open-vocabulary emotion labels from a video. In the MER-OV (Open-Word Emotion Recognition) of the MER2024 challenge, our method achieved significant advantages, leading to its superior capabilities in complex emotion computation.
  arXiv  Detail & Related papers  (2024-08-21T02:17:18Z)
• SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition [65.19303535139453]
  We present our winning approach for the MER-NOISE and MER-OV tracks of the MER2024 Challenge on multimodal emotion recognition. Our system leverages the advanced emotional understanding capabilities of Emotion-LLaMA to generate high-quality annotations for unlabeled samples. For the MER-OV track, our utilization of Emotion-LLaMA for open-vocabulary annotation yields an 8.52% improvement in average accuracy and recall compared to GPT-4V.
  arXiv  Detail & Related papers  (2024-08-20T02:46:03Z)
• 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)
• AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations [57.99479708224221]
  We propose a novel framework called AIMDiT to solve the problem of multimodal fusion of deep features. Experiments conducted using our AIMDiT framework on the public benchmark dataset MELD reveal 2.34% and 2.87% improvements in terms of the Acc-7 and w-F1 metrics.
  arXiv  Detail & Related papers  (2024-04-12T11:31:18Z)
• LastResort at SemEval-2024 Task 3: Exploring Multimodal Emotion Cause Pair Extraction as Sequence Labelling Task [3.489826905722736]
  SemEval 2024 introduces the task of Multimodal Emotion Cause Analysis in Conversations. This paper proposes models that tackle this task as an utterance labeling and a sequence labeling problem. In the official leaderboard for the task, our architecture was ranked 8th, achieving an F1-score of 0.1759 on the leaderboard.
  arXiv  Detail & Related papers  (2024-04-02T16:32:49Z)
• EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation [34.24557248359872]
  We propose an emotional inertia and contagion-driven dependency modeling approach (EmotionIC) for ERC task. Our EmotionIC consists of three main components, i.e., Identity Masked Multi-Head Attention (IMMHA), Dialogue-based Gated Recurrent Unit (DiaGRU) and Skip-chain Conditional Random Field (SkipCRF) Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-20T13:58:35Z)
• FAF: A novel multimodal emotion recognition approach integrating face, body and text [13.485538135494153]
  We develop a large multimodal emotion dataset, named "HED" dataset, to facilitate the emotion recognition task. To promote recognition accuracy, "Feature After Feature" framework was used to explore crucial emotional information. We employ various benchmarks to evaluate the "HED" dataset and compare the performance with our method.
  arXiv  Detail & Related papers  (2022-11-20T14:43:36Z)
• M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database [139.08528216461502]
  We propose a Multi-modal Multi-scene Multi-label Emotional Dialogue dataset, M3ED. M3ED contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9,082 turns and 24,449 utterances. To the best of our knowledge, M3ED is the first multimodal emotional dialogue dataset in Chinese.
  arXiv  Detail & Related papers  (2022-05-09T06:52:51Z)
• 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.