Enhancing Object Detection in YouTube Thumbnails Forensics with YOLOv4
Enhancing Object Detection in YouTube Thumbnails Forensics with YOLOv4
复制标题
DOI：
10.1109/bigdata59044.2023.10386427
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Shahrzad Sayyafzadeh;Hongmei Chi;Shuyuan Mary Ho;Idongesit Mkpong-Ruffin
中科院分区：
文献类型：
--
作者：
Shahrzad Sayyafzadeh;Hongmei Chi;Shuyuan Mary Ho;Idongesit Mkpong-Ruffin
YouTube缩略图作为视觉指示符起着至关重要的作用，它与视频标题和描述一起简洁地捕捉视频的精髓。除了单纯的预览功能外，这些缩略图已经演变成具有磁盘映像加密影响的重要数字产物。本研究深入探讨了将先进的YOLOv4（You Only Look Once，你只需看一次）算法潜在地集成到创建YouTube缩略图中。YOLOv4通过自动识别并强调这些视觉预览中感兴趣的对象来优化这一过程。本文使数据集多样化以提高模型的有效性，扩展其更有效地识别和突出对象的能力。我们通过扩大训练数据、纳入认证以及解密数据集使其与现实世界的缩略图图像相符来应对数据安全挑战。主要目标是评估YOLOv4目标检测模型在经过认证的YouTube缩略图视频中的功效。该网络经过训练可识别80个对象类别，实现了90%的预测率和92%的置信率。
YouTube thumbnails play a vital role as visual indicators, succinctly capturing the essence of a video alongside its title and description. Beyond mere previews, these thumbnails have evolved into significant digital artifacts with implications for disk image encryption. This research delves into potentially integrating the advanced YOLOv4 (You Only Look Once) algorithm into creating YouTube thumbnails. YOLOv4 enhances the process by automatically identifying and emphasizing objects of interest in these visual previews. This paper diversifies the dataset to improve the model’s effectiveness, expanding its capacity to recognize and highlight objects more effectively. We address data security challenges by broadening the training data, incorporating authentication, and decrypting the dataset to align it with real-world thumbnail images. The primary objective is to assess the efficacy of YOLOv4 object detection models in authenticated YouTube thumbnail videos. The network underwent training to recognize 80 object classes, achieving a 90% prediction rate and a 92% confidence rate.