TE-TAD：通过时间对齐坐标表达迈向完全端到端时序动作检测
TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
AI总结：
该研究提出TE-TAD，通过实际时间轴的时间对齐坐标表达和自适应查询选择，消除TAD中对手工组件的依赖，实现完全端到端检测并取得有竞争力的性能。
摘要：
本文研究发现，在用于时序动作检测（TAD）的基于查询的检测器中，归一化坐标表达是导致其依赖手工组件的关键因素。尽管目标检测在端到端框架方面已取得显著进展，但基于查询的检测器在TAD中仍难以实现完全端到端建模。为解决这一问题，我们提出TE-TAD，这是一种融合时间对齐坐标表达的完全端到端时序动作检测transformer。我们利用实际时间轴数值重新表述坐标表达，从而在视频时长极其多样的环境中确保长度不变的表示。此外，我们提出的自适应查询选择会根据视频长度动态调整查询数量，与固定查询集相比，为不同视频时长提供了合适的解决方案。我们的方法不仅通过消除对手工组件的需求简化了TAD流程，还显著提升了基于查询的检测器性能。我们的TE-TAD优于以往基于查询的检测器，并在常用基准数据集上取得了与最先进方法相比具有竞争力的性能。代码可在 https://github.com/Dotori-HJ/TE-TAD 获取。
英文摘要：
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an end-to-end framework in object detection, query-based detectors have been limited in achieving full end-to-end modeling in TAD. To address this issue, we propose \modelname{}, a full end-to-end temporal action detection transformer that integrates time-aligned coordinate expression. We reformulate coordinate expression utilizing actual timeline values, ensuring length-invariant representations from the extremely diverse video duration environment. Furthermore, our proposed adaptive query selection dynamically adjusts the number of queries based on video length, providing a suitable solution for varying video durations compared to a fixed query set. Our approach not only simplifies the TAD process by eliminating the need for hand-crafted components but also significantly improves the performance of query-based detectors. Our TE-TAD outperforms the previous query-based detectors and achieves competitive performance compared to state-of-the-art methods on popular benchmark datasets. Code is available at: https://github.com/Dotori-HJ/TE-TAD
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。
