Sign Language Video Anonymization
Sign Language Video Anonymization
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Zhaoyang Xia;Yuxiao Chen;Qilong Zhangli;Matt Huenerfauth;C. Neidle;Dimitris N. Metaxas
中科院分区：
文献类型：
--
作者：
Zhaoyang Xia;Yuxiao Chen;Qilong Zhangli;Matt Huenerfauth;C. Neidle;Dimitris N. Metaxas
希望用母语交流的聋人签名者经常在网上分享视频。然而，视频不能保护隐私--这通常是讨论敏感话题时所希望的--因为手和脸都传达了关键的语言信息，因此在不降低沟通质量的情况下无法被遮蔽。聋人签名者已经表达了对视频匿名化的兴趣，这将保留语言内容。然而，到目前为止，开发这种技术的尝试取得的成功有限。我们正在开发一种新的匿名化方法，由ASL签名者提供意见。我们修改了一个基于运动的图像动画模型来生成高分辨率的视频，改变了签名者的身份，但保留了语言上有意义的动作和面部表情。非对称编解码器结构的图像生成器用于基于光流和置信度图从低分辨率源帧生成高分辨率目标帧。我们通过使用包围盒来改进损失计算，显式地引导模型获得清晰的手和脸的生成。FID和KID分数用于评估生成的帧的真实感。这项技术在实际应用中显示出巨大的潜力，使聋人签名者受益。
Deaf signers who wish to communicate in their native language frequently share videos on the Web. However, videos cannot preserve privacy—as is often desirable for discussion of sensitive topics—since both hands and face convey critical linguistic information and therefore cannot be obscured without degrading communication. Deaf signers have expressed interest in video anonymization that would preserve linguistic content. However, attempts to develop such technology have thus far shown limited success. We are developing a new method for such anonymization, with input from ASL signers. We modify a motion-based image animation model to generate high-resolution videos with the signer identity changed, but with the preservation of linguistically significant motions and facial expressions. An asymmetric encoder-decoder structured image generator is used to generate the high-resolution target frame from the low-resolution source frame based on the optical flow and confidence map. We explicitly guide the model to attain a clear generation of hands and faces by using bounding boxes to improve the loss computation. FID and KID scores are used for the evaluation of the realism of the generated frames. This technology shows great potential for practical applications to benefit deaf signers.