Detecting Scene Changes in Audiovisual Content
The Netflix TechBlog
JUNE 20, 2023
In the second approach, we show that a relatively simple, supervised sequential model (bidirectional LSTM or GRU) that uses rich, pretrained shot-level embeddings can outperform the current state-of-the-art baselines on our internal benchmarks. However, it presupposes the availability of high-quality screenplays.
Let's personalize your content