TY - GEN
T1 - 2nd Place scheme on action recognition track of ECCV 2020 VIPriors challenges: An efficient optical flow stream guided framework
AU - Chen, H.
AU - Yu, Z.
AU - Liu, X.
AU - Peng, W.
AU - Lee, Y.
AU - Zhao, G.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85170587268&partnerID=MN8TOARS
U2 - 10.48550/arxiv.2008.03996
DO - 10.48550/arxiv.2008.03996
M3 - Other contribution
ER -