用强化学习动态调整模型参数，让视频异常检测更智能、更适应新场景。
COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
- 根据视频片段内容生成专属参数更新，动态适配冻结的视觉语言模型。
- 在标准数据集上超越静态基线，跨域检测准确率提升显著。
- 不仅适用于异常检测，还可推广至问答和密集描述等新任务。
视觉语言模型（VLM）在视频异常检测（VAD）中表现出色，且预测结果可解释。然而，现有基于VLM的方法在训练与推理阶段存在数据分布和模型配置的根本不匹配问题：一是多数方法依赖静态的后训练调整，难以应对未见环境或异常类型；二是训练时使用长视频中的稀疏帧，而推理时却对密集采样的短片段进行处理，导致训练与测试不一致。为此，本文提出COPRA，一种基于强化学习的条件参数自适应框架，用于VLM-based VAD。不同于固定提示或共享参数更新，COPRA在训练和推理过程中为每个视频片段生成输入相关的参数更新，动态适配冻结的VLM。实验表明，COPRA在标准VAD基准上表现优异，在域内和跨域设置下均持续优于静态基线。此外，COPRA还能泛化至未见任务，如多选视频问答和密集字幕生成。这些结果表明，COPRA是一种高效、可扩展、上下文感知的权重空间生成框架，适用于大规模视频理解。
原文摘要 · Abstract (English)
Vision-language models (VLMs) have shown strong performance in video anomaly detection (VAD) while providing interpretable predictions. However, existing VLM-based VAD methods suffer from a fundamental mismatch between training and inference in both data distribution and model configuration. First, most approaches rely on static post-training adaptation, limiting generalization under distribution shifts such as unseen environments or anomaly types. Second, they train VLMs on sparse frames from long videos, but perform inference on densely sampled short segments, creating inconsistencies between training and testing. To address these limitations, we propose COPRA, a conditional parameter adaptation framework for VLM-based VAD. Instead of fixed prompts or shared parameter updates, COPRA generates input-specific parameter updates to dynamically adapt a frozen VLM for each video segment during both training and inference. Experiments show strong performance on standard VAD benchmarks, consistently outperforming static baselines in both in-domain and cross-domain settings. Moreover, COPRA generalizes beyond VAD to unseen tasks such as multiple-choice Video Question Answering and Dense Captioning. These results highlight COPRA as an effective weight-space generation framework for scalable, adaptive, and context-aware video understanding. The code will be released at https://github.com/THE-MALT-LAB/COPRA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。