BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

15 Sep 2020  ·  Haisheng Su, Weihao Gan, Wei Wu, Yu Qiao, Junjie Yan ·

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving. In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation. First, we propose a novel boundary regressor based on the complementary characteristics of both starting and ending boundary classifiers. Specifically, we utilize the U-shaped architecture with nested skip connections to capture rich contexts and introduce bi-directional boundary matching mechanism to improve boundary precision. Second, to account for the proposal-proposal relations ignored in previous methods, we devise a proposal relation block to which includes two self-attention modules from the aspects of position and channel. Furthermore, we find that there inevitably exists data imbalanced problems in the positive/negative proposals and temporal durations, which harm the model performance on tail distributions. To relieve this issue, we introduce the scale-balanced re-sampling strategy. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, which demonstrate that BSN++ achieves the state-of-the-art performance. Not surprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNet challenge leaderboard on temporal action localization task.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Temporal Action Proposal Generation ActivityNet-1.3 BSN++ AUC (val) 68.26 # 6
AR@100 76.52 # 6
Temporal Action Localization ActivityNet-1.3 BSN++ mAP IOU@0.5 51.27 # 15
mAP 34.88 # 21
mAP IOU@0.75 35.70 # 14
mAP IOU@0.95 8.33 # 14

Methods


No methods listed for this paper. Add relevant methods here