English

Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation

Computer Vision and Pattern Recognition 2017-08-02 v1

Abstract

In this work, we address the problem of spatio-temporal action detection in temporally untrimmed videos. It is an important and challenging task as finding accurate human actions in both temporal and spatial space is important for analyzing large-scale video data. To tackle this problem, we propose a cascade proposal and location anticipation (CPLA) model for frame-level action detection. There are several salient points of our model: (1) a cascade region proposal network (casRPN) is adopted for action proposal generation and shows better localization accuracy compared with single region proposal network (RPN); (2) action spatio-temporal consistencies are exploited via a location anticipation network (LAN) and thus frame-level action detection is not conducted independently. Frame-level detections are then linked by solving an linking score maximization problem, and temporally trimmed into spatio-temporal action tubes. We demonstrate the effectiveness of our model on the challenging UCF101 and LIRIS-HARL datasets, both achieving state-of-the-art performance.

Keywords

Cite

@article{arxiv.1708.00042,
  title  = {Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation},
  author = {Zhenheng Yang and Jiyang Gao and Ram Nevatia},
  journal= {arXiv preprint arXiv:1708.00042},
  year   = {2017}
}

Comments

Accepted at BMVC 2017 (oral)

R2 v1 2026-06-22T21:02:47.552Z