arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1911.08548cs.CV
收藏

跨类关联学习的时间概念定位

Cross-Class Relevance Learning for Temporal Concept Localization

Layer6 AI(Layer6人工智能公司)

Junwei Ma, Satya Krishna Gorti, Maksims Volkovs, Ilya Stanevich, Guangwei Yu

摘要:

我们提出了一种新的跨类相关学习的时间概念定位的任务。大多数本地化架构依赖于特征提取层,然后是输出每个片段的类别概率的分类层。然而,在许多现实世界的应用程序中,类可能表现出复杂的关系,难以用这种体系结构进行建模。相比之下,我们建议将目标类和类相关的功能作为输入,并学习一个成对的二进制模型来预测一般段类的相关性。这有助于学习类之间的共享信息,并允许任意类特定的特征工程。我们将这种方法应用于第三届YouTube-8 M视频理解挑战赛,并与其他领先的模型一起,在280多支队伍中获得第一名。在本文中,我们描述了我们的方法,并显示了一些实证结果。

英文摘要:

We present a novel Cross-Class Relevance Learning approach for the task of temporal concept localization. Most localization architectures rely on feature extraction layers followed by a classification layer which outputs class probabilities for each segment. However, in many real-world applications classes can exhibit complex relationships that are difficult to model with this architecture. In contrast, we propose to incorporate target class and class-related features as input, and learn a pairwise binary model to predict general segment to class relevance. This facilitates learning of shared information between classes, and allows for arbitrary class-specific feature engineering. We apply this approach to the 3rd YouTube-8M Video Understanding Challenge together with other leading models, and achieve first place out of over 280 teams. In this paper we describe our approach and show some empirical results.

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。

↑