"In this competition, you are challenged to develop classification algorithms which accurately assign video-level labels using the new and improved YT-8M V2 dataset. The dataset was created from over 7 million YouTube videos (450,000 hours of video) and includes video labels from a vocabulary of 4716 classes (3.4 labels/video on average). It also comes with pre-extracted audio & visual features from every second of video (3.2B feature vectors in total). By taking part, Kagglers will not only play a pivotal role in setting state-of-the-art benchmarks, but also improve search and organization of video archives."