论文标题
低分辨率的行动识别微小行动挑战
Low-Resolution Action Recognition for Tiny Actions Challenge
论文作者
论文摘要
微小的行动挑战的重点是了解现实世界中的人类活动。基本上，在这种情况下，活动识别有两个主要困难。首先，人类活动通常在远处记录，并以小分辨率出现，没有太多歧视性线索。其次，这些活动是自然而然地以一种长尾的方式分发的。很难减轻这种沉重类别失衡的数据偏见。为了解决这些问题，我们在本文中提出了一种全面的识别解决方案。首先，我们训练具有数据平衡的视频骨干，以减轻挑战基准中的过度拟合。其次，我们设计了一个双分辨率蒸馏框架，可以通过超分辨率知识有效地指导低分辨率的行动识别。最后，我们将模型融合到后处理中，这可以进一步提高长尾类别的每种形式。我们的解决方案在排行榜上排名第一。
Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and appear in a small resolution without much discriminative clue. Second, these activities are naturally distributed in a long-tailed way. It is hard to alleviate data bias for such heavy category imbalance. To tackle these problems, we propose a comprehensive recognition solution in this paper. First, we train video backbones with data balance, in order to alleviate overfitting in the challenge benchmark. Second, we design a dual-resolution distillation framework, which can effectively guide low-resolution action recognition by super-resolution knowledge. Finally, we apply model en-semble with post-processing, which can further boost per-formance on the long-tailed categories. Our solution ranks Top-1 on the leaderboard.
