Online Detection of Action Start in Untrimmed, Streaming Videos
Zheng Shou, Junting Pan, Jonathan Chan, Kazuyuki Miyazawa, Hassan Mansour, Anthony Vetro, Xavier Giro-i-Nieto, Shih-Fu Chang
Abstract
We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy and low detection latency. ODAS is important in many applications such as early alert generation to allow timely security or emergency response. We propose three novel methods to specifically address the challenges in training ODAS models: (1) hard negative samples generation based on Generative Adversarial Network (GAN) to distinguish ambiguous background, (2) explicitly modeling the temporal consistency between data around action start and data succeeding action start, and (3) adaptive sampling strategy to handle the scarcity of training data. We conduct extensive experiments using THUMOS'14 and ActivityNet. We show that our proposed methods lead to significant performance gains and improve the state-of-the-art methods. An ablation study confirms the effectiveness of each proposed method.
BibTeX
@inproceedings{eccv2018_onlinedetectiono,
title = {Online Detection of Action Start in Untrimmed, Streaming Videos},
author = {Zheng Shou and Junting Pan and Jonathan Chan and Kazuyuki Miyazawa and Hassan Mansour and Anthony Vetro and Xavier Giro-i-Nieto and Shih-Fu Chang},
booktitle = {ECCV 2018},
year = {2018}
}