面向品牌的社交媒体就绪文案生成
Social Media Ready Caption Generation for Brands
AI总结：
针对开源多模态LLM无法将品牌个性融入社交媒体文案的问题，提出一种基于图像描述与个性对齐生成的双阶段pipeline架构，支持自定义标签和实体，在定性与定量评估中均证明有效。
摘要：
社交媒体广告是品牌营销的关键，旨在通过吸引人的文案和图片或标志来吸引消费者。虽然以往的研究侧重于为一般图像生成文案，但将品牌个性融入社交媒体文案生成仍未被探索。品牌个性被证明会影响消费者的行为和社交互动，因此是营销策略的关键方面。当前的开源多模态 LLM 并不直接适合此任务。因此，我们提出了一种 pipeline 解决方案，以协助品牌创建与图像和品牌个性相一致的引人入胜的社交媒体文案。我们的架构基于两个部分：a 第一部分包含一个 image captioning 模型，该模型接收品牌想要在线发布的图像并给出一个纯英文 caption；b 第二部分接收生成的 caption 以及目标品牌个性，并输出一个吸引人的、与个性对齐的社交媒体文案。除了品牌个性外，我们的系统还允许用户提供他们希望文案包含的 hashtags、Instagram handles、URLs 和 named entities，使文案在语义上与社交媒体账号更相关。与各种 baselines 的比较评估在定性和定量上均证明了我们方法的有效性。
英文摘要：
Social media advertisements are key for brand marketing, aiming to attract consumers with captivating captions and pictures or logos. While previous research has focused on generating captions for general images, incorporating brand personalities into social media captioning remains unexplored. Brand personalities are shown to be affecting consumers' behaviours and social interactions and thus are proven to be a key aspect of marketing strategies. Current open-source multimodal LLMs are not directly suited for this task. Hence, we propose a pipeline solution to assist brands in creating engaging social media captions that align with the image and the brand personalities. Our architecture is based on two parts: a the first part contains an image captioning model that takes in an image that the brand wants to post online and gives a plain English caption; b the second part takes in the generated caption along with the target brand personality and outputs a catchy personality-aligned social media caption. Along with brand personality, our system also gives users the flexibility to provide hashtags, Instagram handles, URLs, and named entities they want the caption to contain, making the captions more semantically related to the social media handles. Comparative evaluations against various baselines demonstrate the effectiveness of our approach, both qualitatively and quantitatively.
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。
