Abstract
The rapid growth of visual content consumption across platforms necessitates automated video classification for age-suitability standards like the MPAA rating system (G, PG, PG-13, R). Traditional methods struggle with large labeled data requirements, poor generalization, and inefficient feature learning. To address these challenges, we employ contrastive learning for improved discrimination and adaptability, exploring three frameworks: Instance Discrimination, Contextual Contrastive Learning, and Multi-View Contrastive Learning. Our hybrid architecture integrates an LRCN (CNN+LSTM) backbone with a Bahdanau attention mechanism, achieving state-of-the-art performance in the Contextual Contrastive Learning framework, with 88% accuracy and an F1 score of 0.8815. By combining CNNs for spatial features, LSTMs for temporal modeling, and attention mechanisms for dynamic frame prioritization, the model excels in fine-grained borderline distinctions, such as differentiating PG-13 and R-rated content. We evaluate the model's performance across various contrastive loss functions, including NT-Xent, NT-logistic, and Margin Triplet, demonstrating the robustness of our proposed architecture. To ensure practical application, the model is deployed as a web application for real-time MPAA rating classification, offering an efficient solution for automated content compliance across streaming platforms.
Abstract (translated)
随着跨平台视觉内容消费的快速增长，对自动视频分类的需求日益增加，特别是在像MPAA评级系统（G、PG、PG-13、R）这样的年龄适宜性标准方面。传统的分类方法面临着大规模标注数据需求高、泛化能力差以及特征学习效率低下的挑战。为了解决这些问题，我们采用了对比学习以提高区分能力和适应性，并探索了三种框架：实例鉴别（Instance Discrimination）、上下文对比学习（Contextual Contrastive Learning）和多视图对比学习（Multi-View Contrastive Learning）。我们的混合架构结合了LRCN（CNN+LSTM）主干网络与Bahdanau注意力机制，在上下文对比学习框架中表现出色，达到了88%的准确率和0.8815的F1分数。通过将卷积神经网络用于空间特征提取、长短期记忆网络用于时间建模以及使用注意力机制进行动态帧优先级排序，该模型在细微区分PG-13与R评级内容方面表现尤为出色。 我们在多种对比损失函数（包括NT-Xent、NT-logistic和Margin Triplet）下评估了模型的性能，展示了我们提出的架构的强大鲁棒性。为了确保实际应用的有效性，我们将模型部署为一个网页应用程序，以实现实时MPAA评分分类，在流媒体平台上提供自动化内容合规解决方案。
URL
https://arxiv.org/abs/2509.06826
