论文标题
在ECCV 2020 VIPRIORS挑战的行动识别轨迹上的第二名方案：有效的光流引导框架
2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework
论文作者
论文摘要
为了解决针对行动识别任务的小数据集上的培训问题，大多数先前的作品要么基于大量培训样本，要么需要从其他大型数据集中传输的预训练模型来解决过度拟合问题。但是，它限制了具有强大计算能力的组织内的研究。在这项工作中，我们尝试提出一个数据效率的框架，该框架可以在小数据集上从头开始训练模型，同时实现有希望的结果。具体而言，通过引入3D中央差卷积操作，我们提出了一个新型的C3D神经网络基于两台（RAST PORMING RGB和光流）框架的框架。该方法在ECCV 2020 Vipriors挑战的动作识别轨道上进行了验证，并获得了第二名（88.31％）。事实证明，即使没有大规模数据集的预培训模型，我们的方法也可以实现有希望的结果。该代码将很快发布。
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D neural network-based two-stream (Rank Pooling RGB and Optical Flow) framework for the task. The method is validated on the action recognition track of the ECCV 2020 VIPriors challenges and got the 2nd place (88.31%). It is proved that our method can achieve a promising result even without a pre-trained model on large scale datasets. The code will be released soon.
