We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a novel representation for ranking these proposals. Since pooling features only inside a segment is not sufficient to predict activity boundaries, we construct a representation which explicitly captures context around a proposal for ranking it. For each temporal segment inside a proposal, features are uniformly sampled at a pair of scales and are input to a temporal convolutional neural network for classification. After ranking proposals, non-maximum suppression is applied and classification is performed to obtain final detections. TCN outperforms state-of-the-art methods on the ActivityNet dataset and the THUMOS14 dataset.
@article{arxiv.1708.02349,
title = {Temporal Context Network for Activity Localization in Videos},
author = {Xiyang Dai and Bharat Singh and Guyue Zhang and Larry S. Davis and Yan Qiu Chen},
journal= {arXiv preprint arXiv:1708.02349},
year = {2017}
}