Deep Metric Learning for Near-Duplicate Video Retrieval Leveraging Efficient Semantic Feature Extraction

Abstract

Video sharing platforms like YouTube, TikTok and Instagram have gained popularity in the online space. Daily several videos are uploaded, which calls for an efficient video retrieval system that could identify near-duplicate videos that offers several advantages in content management, copyright protection, and multimedia retrieval. This will facilitate efficient content management by removal of redundant videos from large repositories to streamline storage resources and improve accessibility of multimedia collections. Additionally, this can help copyright protection and intellectual property allowing right holders to identify unauthorized copies of their original work. Moreover, in applications such as multimedia retrieval and recommendation systems, removal of near-duplicate videos can enhance user experience by providing relevant search results. AI provides a promising solution to this problem. We have proposed an effective system built on deep metric learning that solves the near duplicate video retrieval. This proposed model uses the pre-trained VGG-16 network that contains convolutional and fully connected layers to find video features. These video representations are fed to the deep metric learning framework in the form of triplets which are trained to calculate the accurate distance between similar or near-duplicate videos. For the training of the framework, VCDB dataset was used whereas for the evaluation of the model CC_WEB_VIDEO and TRECVID BBC Rushes 2007 datasets were used. Experiments have shown that mean average precision of 0.985% for the CC_WEB_VIDEO dataset is achieved thus outperforming the state-of-the-art models.