Online detection of action start in untrimmed, streaming videos
Document typeConference lecture
Rights accessOpen Access
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.
This is a post-peer-review, pre-copyedit version of an article published in: Lecture Notes in Computer Sciences, vol. 11207. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-030-01219-9_33
CitationShou, Z., Pan, J., Chan, J., Miyazawa, K., Mansour, H., Vetro, A., Giro, X., Chang, S. Online detection of action start in untrimmed, streaming videos. A: European Conference on Computer Vision. "Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, proceedings, part I". Berlín: Springer, 2018, p. 551-568.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder