VideoLT: Large-scale Long-tailed Video Recognition
This addresses the challenge of biased models in real-world video recognition due to imbalanced label distributions, representing an incremental step by adapting long-tailed recognition from images to videos.
The authors tackled the problem of long-tailed video recognition by introducing VideoLT, a large-scale dataset with 256,218 videos across 1,004 classes, and proposed FrameStack, a method that improves classification performance without sacrificing overall accuracy.
Label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, limited effort has been made for video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. Our VideoLT contains 256,218 untrimmed videos, annotated into 1,004 classes with a long-tailed distribution. Through extensive studies, we demonstrate that state-of-the-art methods used for long-tailed image recognition do not perform well in the video domain due to the additional temporal dimension in video data. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition task. In particular, FrameStack performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training. Experimental results demonstrate that FrameStack can improve classification performance without sacrificing overall accuracy. Code and dataset are available at: https://github.com/17Skye17/VideoLT.