论文标题
BSN ++：时间动作提案生成的互补边界回归器与比例平衡关系建模
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
论文作者
论文摘要
在未修剪视频中生成人类行动建议是一项重要但艰巨的任务。当前的方法通常遭受嘈杂的边界位置和用于检索提案的置信分数的劣质质量。在本文中，我们提出了BSN ++，这是一个新框架，可利用时间提案生成的互补边界回归和关系建模。首先，我们根据启动和结束边界分类器的互补特性提出了一种新颖的边界回归器。具体而言，我们利用带有嵌套跳过连接的U形体系结构来捕获丰富的上下文，并引入双向边界匹配机制来提高边界精度。其次，为了说明以前方法中忽略的提案质量关系，我们设计了一个提案关系块，其中包括来自位置和渠道方面的两个自我发项式模块。此外，我们发现不可避免地存在数据不平衡的问题，这些问题不平衡，在正/负建议和时间持续时间内损害了尾部分布的模型性能。为了缓解这个问题，我们介绍了规模平衡的重新采样策略。广泛的实验是在两个流行的基准上进行的：ActivityNet-1.3和Thumos14，这表明BSN ++实现了最新的性能。毫不奇怪，所提出的BSN ++在CVPR19-活动网站本地化任务中排名第一的CVPR19-活动网络挑战排行榜。
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.
