Indonesian, spoken by over 200 million people, remains underserved in multimodal emotion recognition research despite its dominant presence on Southeast Asian social media platforms. We introduce IndoMER, the first multimodal emotion recognition benchmark for Indonesian, comprising 1,944 video segments from 203 speakers with temporally aligned text, audio, and visual annotations across seven emotion categories. The dataset exhibits realistic challenges including cross-modal inconsistency and long-tailed class distributions shaped by Indonesian cultural communication norms. To address these challenges, we propose OmniMER, a multimodal adaptation framework built upon Qwen2.5-Omni that enhances emotion recognition through three auxiliary modality-specific perception tasks: emotion keyword extraction for text, facial expression analysis for video, and prosody analysis for audio. These auxiliary tasks help the model identify emotion-relevant cues in each modality before fusion, reducing reliance on spurious correlations in low-resource settings. Experiments on IndoMER show that OmniMER achieves 0.582 Macro-F1 on sentiment classification and 0.454 on emotion recognition, outperforming the base model by 7.6 and 22.1 absolute points respectively. Cross-lingual evaluation on the Chinese CH-SIMS dataset further demonstrates the generalizability of the proposed framework. The dataset and code are publicly available. https://github.com/yanxm01/INDOMER

翻译：印度尼西亚语使用者超过两亿，尽管其在东南亚社交媒体平台占据主导地位，但在多模态情感识别研究中仍服务不足。我们推出了首个面向印度尼西亚语的多模态情感识别基准数据集IndoMER，该数据集包含来自203位说话者的1,944个视频片段，涵盖七种情感类别，并提供了时间对齐的文本、音频和视觉标注。该数据集呈现了现实场景中的挑战，包括由印度尼西亚文化交际规范导致的跨模态不一致性和长尾类别分布。为应对这些挑战，我们提出了OmniMER——一个基于Qwen2.5-Omni构建的多模态适配框架，通过三个辅助性模态特定感知任务增强情感识别能力：面向文本的情感关键词提取、面向视频的面部表情分析以及面向音频的韵律分析。这些辅助任务帮助模型在融合前识别各模态中与情感相关的线索，从而减少在低资源场景下对虚假相关性的依赖。在IndoMER数据集上的实验表明，OmniMER在情感分类任务上取得了0.582的宏平均F1值，在情感识别任务上达到0.454，分别比基线模型绝对提升了7.6和22.1个百分点。在中文CH-SIMS数据集上的跨语言评估进一步验证了所提框架的泛化能力。数据集与代码已公开：https://github.com/yanxm01/INDOMER