arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.05487cs.CVcs.AI
收藏

基于场景一致性表示学习的视频场景分割

Scene Consistency Representation Learning for Video Scene Segmentation

Shenzhen University(深圳大学);Tencent YouTu Lab(腾讯优图实验室);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);KAUST(阿卜杜拉国王科技大学)

Haoqian Wu, Keyu Chen, Yanan Luo, Ruizhi Qiao, Bo Ren, Haozhe Liu, Weicheng Xie, Linlin Shen

摘要:

一个长时间的视频,如电影或电视节目,是由各种场景组成的,每个场景代表一系列共享相同语义故事的镜头。从长期视频中发现正确的场景边界是一项具有挑战性的任务,因为模型必须了解视频的故事情节,才能确定场景的开始和结束位置。为此,我们提出了一个有效的自监督学习(SSL)框架,学习更好的镜头表示从未标记的长期视频。更具体地说,我们提出了一个SSL方案,以实现场景的一致性,同时探索相当大的数据增强和洗牌方法,以提高模型的泛化能力。我们引入了一个具有较少归纳偏差的香草时间模型来验证镜头特征的质量,而不是像以前的方法那样显式地学习场景边界特征。我们的方法实现了国家的最先进的性能上的视频场景分割的任务。此外,我们建议一个更公平合理的基准来评估视频场景分割方法的性能。代码可用。

英文摘要:

A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑