English

Relation-Aware Pyramid Network (RapNet) for temporal action proposal

Computer Vision and Pattern Recognition 2019-08-12 v1

Abstract

In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 based on Kinetics pretrained model to extract snippet-level video representations and then we design a Relation-Aware Pyramid Network (RapNet) to generate temporal multiscale proposals with confidence score. After that, we employ a two-stage snippet-level boundary adjustment scheme to re-rank the order of generated proposals. Ensemble methods are also been used to improve the performance of our solution, which helps us achieve 2nd place.

Cite

@article{arxiv.1908.03448,
  title  = {Relation-Aware Pyramid Network (RapNet) for temporal action proposal},
  author = {Jialin Gao and Zhixiang Shi and Jiani Li and Yufeng Yuan and Jiwei Li and Xi Zhou},
  journal= {arXiv preprint arXiv:1908.03448},
  year   = {2019}
}

Comments

Submission to temporal action proposal task in ActivityNet Challenge 2019

R2 v1 2026-06-23T10:43:45.584Z