arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.04018cs.CVeess.IV
收藏

面向协同智能的潜空间运动分析

Analysis of Latent-Space Motion for Collaborative Intelligence

Simon Fraser University(西蒙弗雷泽大学)

Mateen Ulhaq, Ivan V. Bajić

摘要:

当深度神经网络(DNN)的输入是视频信号时,在模型的中间层产生特征张量序列。如果输入视频的相邻帧通过运动相关,那么自然的问题是,“对应的特征张量之间的关系是什么?“通过分析常见DNN操作对光流的影响,我们发现特征张量的每个通道中存在的运动近似等于输入运动的缩放版本。利用常见的运动模型,通过实验验证了分析。%这些结果将是有用的协作智能应用程序中的特征张量序列需要压缩或进一步分析。

英文摘要:

When the input to a deep neural network (DNN) is a video signal, a sequence of feature tensors is produced at the intermediate layers of the model. If neighboring frames of the input video are related through motion, a natural question is, "what is the relationship between the corresponding feature tensors?" By analyzing the effect of common DNN operations on optical flow, we show that the motion present in each channel of a feature tensor is approximately equal to the scaled version of the input motion. The analysis is validated through experiments utilizing common motion models. %These results will be useful in collaborative intelligence applications where sequences of feature tensors need to be compressed or further analyzed.

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。

↑