推进视频异常检测：面向增强单任务与多任务方法的双向混合框架
Advancing Video Anomaly Detection: A Bi-Directional Hybrid Framework for Enhanced Single- and Multi-Task Approaches
AI总结：
针对视频异常检测中单任务框架次优的问题，提出双向混合框架，结合视觉变换器和ConvLSTM进行中间帧预测，通过前后向预测与层交互增强稳定性与细节，实验验证其在单任务和多任务中均有效。
摘要：
尽管视频异常检测领域正从单任务方法向多任务方法过渡，我们观察到许多方法在单个代理任务上采用了次优框架。受此启发，我们认为优化单任务框架可以同时推进单任务和多任务方法。因此，我们采用中间帧预测作为主要代理任务，并引入一个有效的混合框架，旨在为正常帧生成准确预测，为异常帧生成有缺陷的预测。该混合框架基于双向结构构建，无缝集成了视觉变换器和卷积长短期记忆网络。具体而言，我们利用这种双向结构，通过向前和向后两个方向预测帧来全面分析时间维度，显著提升检测稳定性。鉴于变换器具有建模长距离上下文依赖的能力，我们开发了一种卷积时间变换器，它能高效地关联所有上下文帧的特征图，为目标帧生成基于注意力的预测。此外，我们设计了一个层交互式卷积长短期记忆桥，促进低层特征在层间和时间步间的平滑流动，从而以精细细节强化预测。异常最终通过审视目标帧与其对应预测之间的差异来识别。在公开基准上进行的多项实验证实了我们混合框架的有效性，无论其作为独立的单任务方法使用，还是作为多任务方法中的一个分支集成。这些实验还强调了将视觉变换器和卷积长短期记忆网络结合用于视频异常检测的优势。
英文摘要：
Despite the prevailing transition from single-task to multi-task approaches in video anomaly detection, we observe that many adopt sub-optimal frameworks for individual proxy tasks. Motivated by this, we contend that optimizing single-task frameworks can advance both single- and multi-task approaches. Accordingly, we leverage middle-frame prediction as the primary proxy task, and introduce an effective hybrid framework designed to generate accurate predictions for normal frames and flawed predictions for abnormal frames. This hybrid framework is built upon a bi-directional structure that seamlessly integrates both vision transformers and ConvLSTMs. Specifically, we utilize this bi-directional structure to fully analyze the temporal dimension by predicting frames in both forward and backward directions, significantly boosting the detection stability. Given the transformer's capacity to model long-range contextual dependencies, we develop a convolutional temporal transformer that efficiently associates feature maps from all context frames to generate attention-based predictions for target frames. Furthermore, we devise a layer-interactive ConvLSTM bridge that facilitates the smooth flow of low-level features across layers and time-steps, thereby strengthening predictions with fine details. Anomalies are eventually identified by scrutinizing the discrepancies between target frames and their corresponding predictions. Several experiments conducted on public benchmarks affirm the efficacy of our hybrid framework, whether used as a standalone single-task approach or integrated as a branch in a multi-task approach. These experiments also underscore the advantages of merging vision transformers and ConvLSTMs for video anomaly detection.
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。
