论文标题
弱监督视频异常检测中被忽略的视频分类
Overlooked Video Classification in Weakly Supervised Video Anomaly Detection
论文作者
论文摘要
当前弱监督的视频异常检测算法主要使用多个实例学习（MIL）或其品种。几乎所有最近的方法都集中在如何选择正确的片段以提高性能。他们忽略或没有意识到视频分类在提高异常检测性能方面的力量。在本文中，我们使用BERT或LSTM明确研究视频分类监督的力量。使用此BERT或LSTM，可以将视频的所有片段的CNN功能汇总为单个功能，可用于视频分类。这个简单而强大的视频分类监督结合在MIL框架中，在所有三个主要视频异常检测数据集上都具有极大的性能改进。特别是它提高了XD暴力的平均平均精度（MAP）从SOTA 78.84 \％\％到新的82.10 \％。源代码可从https://github.com/wjtan99/bert_anomaly_video_classification获得。
Current weakly supervised video anomaly detection algorithms mostly use multiple instance learning (MIL) or their varieties. Almost all recent approaches focus on how to select the correct snippets for training to improve the performance. They overlook or do not realize the power of video classification in boosting the performance of anomaly detection. In this paper, we study explicitly the power of video classification supervision using a BERT or LSTM. With this BERT or LSTM, CNN features of all snippets of a video can be aggregated into a single feature which can be used for video classification. This simple yet powerful video classification supervision, combined into the MIL framework, brings extraordinary performance improvement on all three major video anomaly detection datasets. Particularly it improves the mean average precision (mAP) on the XD-Violence from SOTA 78.84\% to new 82.10\%. The source code is available at https://github.com/wjtan99/BERT_Anomaly_Video_Classification.
