BAM-DETR：用于视频时间句子定位的边界对齐时刻检测变换器
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
AI总结：
针对DETR式时间定位中中心错位问题，提出面向边界的时刻表述与双路径解码的BAM-DETR，并引入质量排序，在三个基准上验证有效性。
摘要：
时间句子定位旨在定位与语言描述相关的时刻。近期，类似DETR的方法通过预测目标时刻的中心和长度取得了显著进展。然而，这些方法面临由时刻中心固有模糊性引发的中心错位问题，导致预测不准确。为解决此问题，我们提出了一种新颖的面向边界的时刻表述范式。在该范式中，模型无需寻找精确中心，只需预测区间内的任意锚点，并直接据此估计边界。基于此思想，我们设计了边界对齐时刻检测变换器，配备双路径解码过程。具体而言，该模型在并行路径中分别利用全局注意力和边界聚焦注意力细化锚点和边界。这种分离设计使模型能够聚焦于理想区域，实现时刻预测的精确细化。此外，我们提出了一种基于质量的排序方法，确保具有高定位质量的提案优先于不完整的提案。在三个基准上的实验验证了所提方法的有效性。代码可在https://github.com/Pilhyeon/BAM-DETR获取。
英文摘要：
Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions. To remedy this problem, we propose a novel boundary-oriented moment formulation. In our paradigm, the model no longer needs to find the precise center but instead suffices to predict any anchor point within the interval, from which the boundaries are directly estimated. Based on this idea, we design a boundary-aligned moment detection transformer, equipped with a dual-pathway decoding process. Specifically, it refines the anchor and boundaries within parallel pathways using global and boundary-focused attention, respectively. This separate design allows the model to focus on desirable regions, enabling precise refinement of moment predictions. Further, we propose a quality-based ranking method, ensuring that proposals with high localization qualities are prioritized over incomplete ones. Experiments on three benchmarks validate the effectiveness of the proposed methods. The code is available at https://github.com/Pilhyeon/BAM-DETR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
