TLMA：缓解弱标签信息对视频异常检测的影响
TLMA: Mitigating the Impact of Weakly Labeled Information for Video Anomaly Detection
把正常视频中的困难片段当作锚框样本，用对比学习与多示例学习联合拉开异常片段与锚框的投影距离，可直接迁移到其他只有视频级弱标签的时序定位任务（如暴力片段定位、关键事件检测）。
原文依据 we propose a triplet learning strategy that selects hard segments from normal videos as anchors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论弱监督视频异常检测（WSVAD）旨在训练阶段仅使用视频级标签来定位异常片段。尽管该范式显著降低了标注成本，但粗粒度标签无法精确描述完整视频，导致训练过程中引入大量弱标签信息（WLI）。WLI 的存在使模型难以准确学习正常行为与异常行为之间的边界，从而造成误分类并损害异常定位的精度。为应对 WLI 带来的挑战，我们提出一种三元组学习策略，从正常视频中选取困难片段作为锚框。通过将对比学习与多示例学习（MIL）策略相结合，我们增大异常片段与锚框样本之间的投影距离，以减少 WLI 对异常检测的干扰。此外，考虑到异常通常出现在动态前景区域，我们进一步设计了一个运动感知特征增强模块，用于提取每个视频片段内的动态区域，以强化关键特征的表示。这不仅提升了三元组中锚框的准确性，也增强了 MIL 中实例特征的判别能力。在 UCF-Crime、XD-Violence 和 MSAD 数据集上的大量实验证明了本方法的有效性。
英文原文摘要 1419 字符
Weakly Supervised Video Anomaly Detection (WSVAD) aims to localize abnormal segments using only video-level labels during training.Although the paradigm significantly reduces annotation costs, the coarse-grained labels fail to precisely describe the full videos, resulting in the introduction of substantial Weakly Labeled Information (WLI) during training. The presence of WLI makes it difficult for the model to accurately learn the boundary between normal and abnormal behaviors, leading to misclassifications and compromising the precision of anomaly localization.To tackle the challenges posed by WLI, we propose a triplet learning strategy that selects hard segments from normal videos as anchors. By combining contrastive learning with Multiple Instance Learning (MIL) strategy, we increase the projection distance between abnormal segments and anchor samples, to reduce the interference of WLI in anomaly detection.Moreover, considering that anomalies typically occur in dynamic foreground regions, we further design a motion-aware feature enhancement module that extracts dynamic areas within each video segment to emphasize the representation of critical features.This not only improves the accuracy of anchors in triplets, but also enhances the discriminative power of instance features in MIL. Extensive experiments on UCF-Crime, XD-Violence, and MSAD datasets demonstrate the effectiveness of our approach.