论文标题
Opental：朝着开放的时间动作本地化
OpenTAL: Towards Open Set Temporal Action Localization
论文作者
论文摘要
在监督的学习范式下，时间行动本地化（TAL）取得了巨大的成功。但是，现有的TAL方法植根于封闭的假设，该假设无法处理开放世界中的不可避免的不明动作。在本文中，我们第一次迈向开放式TAL（OSTAL）问题，并根据证据深度学习（EDL）提出了一个通用框架。具体而言，蛋白质包括不确定性感知的动作分类，行动性预测和时间位置回归。通过提出的重要性均衡方法，通过从重要样本中收集分类证据来学习分类不确定性。为了区分未知的动作与背景视频框架，动作是通过未标记的学习来学习的。通过利用时间定位质量的指导，进一步校准了分类不确定性。 Opental通常可以为开放场景启用现有的TAL模型，并且对Thumos14和ActivityNet1.3基准的实验结果显示了我们方法的有效性。代码和预训练模型将在https://www.rit.edu/actionlab/opental上发布。
Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in open-world scenarios. In this paper, we, for the first time, step toward the Open Set TAL (OSTAL) problem and propose a general framework OpenTAL based on Evidential Deep Learning (EDL). Specifically, the OpenTAL consists of uncertainty-aware action classification, actionness prediction, and temporal location regression. With the proposed importance-balanced EDL method, classification uncertainty is learned by collecting categorical evidence majorly from important samples. To distinguish the unknown actions from background video frames, the actionness is learned by the positive-unlabeled learning. The classification uncertainty is further calibrated by leveraging the guidance from the temporal localization quality. The OpenTAL is general to enable existing TAL models for open set scenarios, and experimental results on THUMOS14 and ActivityNet1.3 benchmarks show the effectiveness of our method. The code and pre-trained models are released at https://www.rit.edu/actionlab/opental.
