Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation

• URL: http://arxiv.org/abs/2505.18168v1
• Date: Wed, 14 May 2025 03:00:20 GMT
• Title: Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation
• Authors: Feifan Wang, Tengfei Song, Minggui He, Chang Su, Zhanglin Wu, Hao Yang, Wenming Zheng, Osamu Yoshie,
• Abstract summary: We propose a self-verification approach with emotion knowledge enhancement (SEKE) to generate high-quality instruction data for emotion analysis.<n>This approach integrates prior human knowledge to VLLM inference, guided by the inherent correlations between three grained levels of emotion descriptions.<n>A self-verification strategy with Uncertainty-Aware Monte Carlo sampling (SV-UAMC) is further embedded to efficiently extract more accurate VLLM predictions.
• Score: 17.94565281111736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Facial emotion perception in the vision large language model (VLLM) is crucial for achieving natural human-machine interaction. However, creating high-quality annotations for both coarse- and fine-grained facial emotion analysis demands costly expertise. The lack of such high-quality instruction data limits the performance of VLLMs in facial emotion perception. To address this, we propose a self-verification approach with emotion knowledge enhancement (SEKE), which generates high-quality instruction data for multi-grained emotion analysis cost-effectively using closed-source VLLM. This approach integrates prior human knowledge to VLLM inference, guided by the inherent correlations between three grained levels of emotion descriptions, i.e., discrete expression, valence-arousal, and action unit, to reliably generate comprehensive annotations. A self-verification strategy with Uncertainty-Aware Monte Carlo sampling (SV-UAMC) is further embedded to efficiently extract more accurate VLLM predictions, further improving annotation reliability. Consequently, we construct a facial emotion instruction dataset (FEID) containing three comprehensive descriptions, which provides coarse- and fine-grained emotional information for effective model training. Additionally, we introduce a facial emotion analysis benchmark (FEAB) to measure the VLLM's corresponding ability. Our method significantly outperforms state-of-the-art methods on three downstream facial emotion analysis tasks.

Related papers

• DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding [61.26026947423187]
  Human experts excel at fine-grained visual discrimination by leveraging domain knowledge to refine perceptual features.<n>Current Multimodal Large Language Models (MLLMs) struggle to integrate reasoning into visual perception.<n>We propose DeepPerception, an MLLM enhanced with cognitive visual perception capabilities.
  arXiv  Detail & Related papers  (2025-03-17T04:06:34Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Evaluating Vision-Language Models for Emotion Recognition [1.7409710986849658]
  We present the first comprehensive evaluation of Large Vision-Language Models (VLMs) for recognizing evoked emotions from images.<n>Through several experiments, we demonstrate important factors that emotion recognition performance depends on, and also characterize the various errors made by VLMs in the process.
  arXiv  Detail & Related papers  (2025-02-08T18:25:31Z)
• MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis [53.012111671763776]
  This study introduces MEMO-Bench, a comprehensive benchmark consisting of 7,145 portraits, each depicting one of six different emotions. Results demonstrate that existing T2I models are more effective at generating positive emotions than negative ones. Although MLLMs show a certain degree of effectiveness in distinguishing and recognizing human emotions, they fall short of human-level accuracy.
  arXiv  Detail & Related papers  (2024-11-18T02:09:48Z)
• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset [92.99416966226724]
  We introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms.<n>We apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels.<n>Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance.
  arXiv  Detail & Related papers  (2024-11-05T23:26:10Z)
• Self-supervised Gait-based Emotion Representation Learning from Selective Strongly Augmented Skeleton Sequences [4.740624855896404]
  We propose a contrastive learning framework utilizing selective strong augmentation for self-supervised gait-based emotion representation. Our approach is validated on the Emotion-Gait (E-Gait) and Emilya datasets and outperforms the state-of-the-art methods under different evaluation protocols.
  arXiv  Detail & Related papers  (2024-05-08T09:13:10Z)
• Facial Affective Behavior Analysis with Instruction Tuning [58.332959295770614]
  Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. Traditional approaches primarily deploy models to discriminate among discrete emotion categories, and lack the fine granularity and reasoning capability for complex facial behaviors. We introduce an instruction-following dataset for two FABA tasks, emotion and action unit recognition, and a benchmark FABA-Bench with a new metric considering both recognition and generation ability. We also introduce a facial prior expert module with face structure knowledge and a low-rank adaptation module into pre-trained MLLM.
  arXiv  Detail & Related papers  (2024-04-07T19:23:28Z)
• Affective Behaviour Analysis via Integrating Multi-Modal Knowledge [24.74463315135503]
  The 6th competition on Affective Behavior Analysis in-the-wild (ABAW) utilizes the Aff-Wild2, Hume-Vidmimic2, and C-EXPR-DB datasets. We present our method designs for the five competitive tracks, i.e., Valence-Arousal (VA) Estimation, Expression (EXPR) Recognition, Action Unit (AU) Detection, Compound Expression (CE) Recognition, and Emotional Mimicry Intensity (EMI) Estimation.
  arXiv  Detail & Related papers  (2024-03-16T06:26:43Z)
• EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis [33.0280076936761]
  We propose EmoLLMs, the first series of open-sourced instruction-following LLMs for affective analysis based on fine-tuning various LLMs with instruction data. EmoLLMs achieve the ChatGPT-level and GPT-4-level generalization capabilities on affective analysis tasks, and demonstrates our models can be used as affective annotation tools.
  arXiv  Detail & Related papers  (2024-01-16T17:11:11Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)

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.