Temporally smooth online action detection using cycle-consistent future anticipation
This work addresses the problem of real-time video analysis for applications like autonomous driving and surveillance, offering an incremental improvement over existing methods.
The paper tackles online action detection in videos, where decisions must be made in real-time using only current and past frames, by proposing FATSnet, an RNN-based network that anticipates future frames using unsupervised cycle-consistency loss and aggregates past and future for smooth predictions, achieving state-of-the-art performance on TVSeries, THUMOS14, and BBDB datasets.
Many video understanding tasks work in the offline setting by assuming that the input video is given from the start to the end. However, many real-world problems require the online setting, making a decision immediately using only the current and the past frames of videos such as in autonomous driving and surveillance systems. In this paper, we present a novel solution for online action detection by using a simple yet effective RNN-based networks called the Future Anticipation and Temporally Smoothing network (FATSnet). The proposed network consists of a module for anticipating the future that can be trained in an unsupervised manner with the cycle-consistency loss, and another component for aggregating the past and the future for temporally smooth frame-by-frame predictions. We also propose a solution to relieve the performance loss when running RNN-based models on very long sequences. Evaluations on TVSeries, THUMOS14, and BBDB show that our method achieve the state-of-the-art performances compared to the previous works on online action detection.