Enregistré dans:
Détails bibliographiques
Auteurs principaux: Peng, Xiaojiang, Chen, Jingyi, Cheng, Zebang, Peng, Bao, Wu, Fengyi, Dong, Yifei, Tu, Shuyuan, Hu, Qiyu, Huang, Huiting, Lin, Yuxiang, He, Jun-Yan, Wang, Kai, Lian, Zheng, Cheng, Zhi-Qi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.16449
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918350106394624
author Peng, Xiaojiang
Chen, Jingyi
Cheng, Zebang
Peng, Bao
Wu, Fengyi
Dong, Yifei
Tu, Shuyuan
Hu, Qiyu
Huang, Huiting
Lin, Yuxiang
He, Jun-Yan
Wang, Kai
Lian, Zheng
Cheng, Zhi-Qi
author_facet Peng, Xiaojiang
Chen, Jingyi
Cheng, Zebang
Peng, Bao
Wu, Fengyi
Dong, Yifei
Tu, Shuyuan
Hu, Qiyu
Huang, Huiting
Lin, Yuxiang
He, Jun-Yan
Wang, Kai
Lian, Zheng
Cheng, Zhi-Qi
contents Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their capabilities in emotional reasoning remain limited. The field currently suffers from a scarcity of large-scale datasets with high-quality, descriptive emotion annotations and lacks standardized benchmarks for evaluation. Our preliminary framework, Emotion-LLaMA, pioneered instruction-tuned multimodal learning for emotion reasoning but was restricted by explicit face detectors, implicit fusion strategies, and low-quality training data with limited scale. To address these limitations, we present Emotion-LLaMAv2 and the MMEVerse benchmark, establishing an end-to-end pipeline together with a standardized evaluation setting for emotion recognition and reasoning. Emotion-LLaMAv2 introduces three key advances. First, an end-to-end multiview encoder eliminates external face detection and captures nuanced emotional cues via richer spatial and temporal multiview tokens. Second, a Conv Attention pre-fusion module is designed to enable simultaneous local and global multimodal feature interactions external to the LLM backbone. Third, a perception-to-cognition curriculum instruction tuning scheme within the LLaMA2 backbone unifies emotion recognition and free-form emotion reasoning. To support large-scale training and reproducible evaluation, MMEVerse aggregates twelve publicly available emotion datasets, including IEMOCAP, MELD, DFEW, and MAFW, into a unified multimodal instruction format. The data are re-annotated via a multi-agent pipeline involving Qwen2 Audio, Qwen2.5 VL, and GPT 4o, producing 130k training clips and 36k testing clips across 18 evaluation benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16449
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding
Peng, Xiaojiang
Chen, Jingyi
Cheng, Zebang
Peng, Bao
Wu, Fengyi
Dong, Yifei
Tu, Shuyuan
Hu, Qiyu
Huang, Huiting
Lin, Yuxiang
He, Jun-Yan
Wang, Kai
Lian, Zheng
Cheng, Zhi-Qi
Computer Vision and Pattern Recognition
Artificial Intelligence
Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their capabilities in emotional reasoning remain limited. The field currently suffers from a scarcity of large-scale datasets with high-quality, descriptive emotion annotations and lacks standardized benchmarks for evaluation. Our preliminary framework, Emotion-LLaMA, pioneered instruction-tuned multimodal learning for emotion reasoning but was restricted by explicit face detectors, implicit fusion strategies, and low-quality training data with limited scale. To address these limitations, we present Emotion-LLaMAv2 and the MMEVerse benchmark, establishing an end-to-end pipeline together with a standardized evaluation setting for emotion recognition and reasoning. Emotion-LLaMAv2 introduces three key advances. First, an end-to-end multiview encoder eliminates external face detection and captures nuanced emotional cues via richer spatial and temporal multiview tokens. Second, a Conv Attention pre-fusion module is designed to enable simultaneous local and global multimodal feature interactions external to the LLM backbone. Third, a perception-to-cognition curriculum instruction tuning scheme within the LLaMA2 backbone unifies emotion recognition and free-form emotion reasoning. To support large-scale training and reproducible evaluation, MMEVerse aggregates twelve publicly available emotion datasets, including IEMOCAP, MELD, DFEW, and MAFW, into a unified multimodal instruction format. The data are re-annotated via a multi-agent pipeline involving Qwen2 Audio, Qwen2.5 VL, and GPT 4o, producing 130k training clips and 36k testing clips across 18 evaluation benchmarks.
title Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.16449