MemeLens：多语言多任务VLMs用于表情包
MemeLens: Multilingual Multitask VLMs for Memes
AI总结：
本文提出MemeLens，一种统一的多语言多任务解释增强视觉语言模型，用于表情包理解。通过整合38个公开数据集，建立20个任务的共享分类体系，并分析不同模型范式和数据集的表现，发现多模态训练和统一训练对表情包理解至关重要。
摘要：
表情包是在线交流和操控的主要媒介，因为意义来源于嵌入文本、图像和文化背景的相互作用。现有表情包研究分散在多个任务（仇恨、性别歧视、宣传、情感、幽默）和语言中，限制了跨领域泛化。为解决这一差距，我们提出了MemeLens，一种统一的多语言和多任务解释增强视觉语言模型（VLM），用于表情包理解。我们整合了38个公开的表情包数据集，过滤并映射数据集特定的标签到20个任务的共享分类中，涵盖伤害、目标、隐喻/实用意图和情感。我们展示了跨建模范式、任务类别和数据集的全面实证分析。我们的发现表明，稳健的表情包理解需要多模态训练，表现出在语义类别上的显著变化，并且在模型在单个数据集上微调而不是统一训练时仍然敏感。我们公开了实验资源（https://github.com/MohamedBayan/MemeLens）、模型（https://huggingface.co/QCRI/MemeLens-VLM）和数据集（https://huggingface.co/datasets/QCRI/MemeLens）给社区。
英文摘要：
Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (e.g., \textit{hate, misogyny, propaganda, sentiment, humour}) and languages, which limits cross-domain generalization. To address this gap, we propose \textsc{MemeLens}, a unified multilingual, multitask explanation-enhanced Vision-Language Model (VLM) for meme understanding. We consolidate $38$ public meme datasets, filter and map dataset-specific labels into a shared taxonomy of $20$ tasks spanning harm, targets, figurative/pragmatic intent, and affect. We present a comprehensive empirical analysis across modeling paradigms, task categories, and datasets. Our findings suggest that robust meme understanding requires multimodal training, varies substantially across semantic categories, and remains sensitive to over-specialization when models are fine-tuned on individual datasets rather than trained in a unified setting. We make the experimental resources (https://github.com/MohamedBayan/MemeLens), model (https://huggingface.co/QCRI/MemeLens-VLM) and datasets (https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
