Boundary-Aware Cascade Networks for Temporal Action Segmentation
Zhenzhi Wang, Ziteng Gao, Limin Wang, Zhifeng Li, Gangshan Wu
Abstract
Identifying human action segments in an untrimmed video is still challenging due to boundary ambiguity and over-segmentation issues. To address these problems, we present a new boundary-aware cascade network by introducing two novel components. First, we devise a new cascading paradigm, called Stage Cascade, to enable our model to have adaptive receptive fields and more confident predictions for ambiguous frames. Second, we design a general and principled smoothing operation, termed as local barrier pooling, to aggregate local predictions by leveraging semantic boundary information. Moreover, these two components can be jointly fine-tuned in an end-to-end manner. We perform experiments on three challenging datasets: 50Salads, GTEA and Breakfast dataset, demonstrating that our framework significantly out-performs the current state-of-the-art methods. The code is available at https://github.com/MCG-NJU/BCN."
BibTeX
@inproceedings{eccv2020_boundaryawarecas,
title = {Boundary-Aware Cascade Networks for Temporal Action Segmentation},
author = {Zhenzhi Wang and Ziteng Gao and Limin Wang and Zhifeng Li and Gangshan Wu},
booktitle = {ECCV 2020},
year = {2020}
}