With short video platforms becoming one of the important channels for news sharing, major short video platforms in China have gradually become new breeding grounds for fake news. However, it is not easy to distinguish short video rumors due to the great amount of information and features contained in short videos, as well as the serious homogenization and similarity of features among videos. In order to mitigate the spread of short video rumors, our group decides to detect short video rumors by constructing multimodal feature fusion and introducing external knowledge after considering the advantages and disadvantages of each algorithm. The ideas of detection are as follows: (1) dataset creation: to build a short video dataset with multiple features; (2) multimodal rumor detection model: firstly, we use TSN (Temporal Segment Networks) video coding model to extract video features; then, we use OCR (Optical Character Recognition) and ASR (Automatic Character Recognition) to extract video features. Recognition) and ASR (Automatic Speech Recognition) fusion to extract text, and then use the BERT model to fuse text features with video features (3) Finally, use contrast learning to achieve distinction: first crawl external knowledge, then use the vector database to achieve the introduction of external knowledge and the final structure of the classification output. Our research process is always oriented to practical needs, and the related knowledge results will play an important role in many practical scenarios such as short video rumor identification and social opinion control.

翻译：随着短视频平台成为新闻传播的重要渠道之一，我国各大短视频平台逐渐成为虚假新闻的新滋生地。然而，由于短视频中包含海量信息与特征，且视频间特征严重同质化与相似性，区分短视频谣言并非易事。为遏制短视频谣言的扩散，本课题组在权衡各算法优劣后，决定通过构建多模态特征融合并引入外部知识的方式检测短视频谣言。检测思路如下：（1）数据集构建：建立包含多重特征的短视频数据集；（2）多模态谣言检测模型：首先利用TSN（时间分段网络）视频编码模型提取视频特征；其次通过OCR（光学字符识别）与ASR（自动语音识别）融合提取文本特征，进而采用BERT模型融合文本特征与视频特征；（3）最后利用对比学习实现区分：先爬取外部知识，再通过向量数据库实现外部知识的引入并输出最终分类结构。本研究过程始终面向实际需求，相关知识成果将在短视频谣言识别、社会舆论管控等众多实际场景中发挥重要作用。