New CFE-PPAR method enables privacy-preserving video action recognition with compression

Researchers have introduced CFE-PPAR, a novel method for privacy-preserving action recognition in videos that remains effective even after compression. Unlike previous approaches that suffer significant performance degradation when encrypted videos are compressed, CFE-PPAR allows video transformers to directly recognize encrypted content. This is achieved by using parameters transformed with the same keys used for video encryption, demonstrating superior performance on the UCF101 and HMDB51 datasets under common compression standards like Motion-JPEG and H.264. AI

影响 Introduces a method to maintain AI video analysis accuracy on compressed, privacy-protected data.

排序理由 This is a research paper detailing a new method for privacy-preserving action recognition. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• H.264
• CFE-PPAR
• HMDB51
• Motion-JPEG
• UCF101

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →