Abstract
Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance of (1) boundary prediction and (2) top-1 prediction selection during inference. In their boundary prediction, boundaries are simply set at half a standard deviation away from a Gaussian mean on both sides, which may not accurately capture the optimal boundaries. In the top-1 prediction process, these existing methods rely heavily on intersections with other proposals, without considering the varying quality of each proposal. To address these issues, we explore various inference strategies by introducing (1) novel boundary prediction methods to capture diverse boundaries from multiple Gaussians and (2) new selection methods that take proposal quality into account. Extensive experiments on the ActivityNet Captions and Charades-STA datasets validate the effectiveness of our inference strategies, demonstrating performance improvements without requiring additional training.
Abstract (translated)
弱监督视频定位的目标是在没有明确的时间边界标注的情况下，找到与给定查询相关的时间边界。现有方法主要使用基于高斯分布的提案（proposals），但它们忽略了两个关键点：(1) 边界预测的重要性以及 (2) 在推理过程中选择最佳单一提案的重要性。 在现有的边界预测中，边界通常简单地设置为从高斯分布均值出发，在两侧各半标准差的位置。这种做法可能无法准确捕捉到最优的时间边界。而在选择最有可能的单一提案时，现有方法主要依赖于与其他提案的重叠部分（intersections），而没有考虑到每个提案的质量差异。 为了应对这些问题，我们探索了多种推理策略，包括：(1) 引入新的边界预测方法来从多个高斯分布中捕捉多样化的边界；以及 (2) 采用新的选择方法考虑提案质量。在ActivityNet Captions和Charades-STA数据集上的广泛实验验证了我们的推理策略的有效性，并且展示了在不需额外训练的情况下性能的提升。
URL
https://arxiv.org/abs/2503.23181
