VideoLT: Large-scale Long-tailed Video Recognition

ICCV(2021)

引用 30|浏览75
暂无评分
摘要
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 the video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. 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 videos. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition. 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 the overall accuracy. Code and dataset are available at: https://github.com/17Skye17/VideoLT.
更多
查看译文
关键词
videolt recognition,large-scale,long-tailed
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要