首页MK-MMD和交叉熵损失函数

MK-MMD和交叉熵损失函数

时间: 2023-11-07 08:54:32 浏览: 350

用于人体动作识别的PKU-MMD大范围数据集

Despite the fact that many 3D human activity benchmarks being proposed, most existing action datasets focus on the action recognition tasks for the segmented videos. There is a lack of standard large-scale benchmarks, especially for current popular data-hungry deep learning based methods. In this paper, we introduce a new large scale benchmark (PKU-MMD) for continuous multi-modality 3D human action understanding and cover a wide range of complex human activities with well annotated information. PKU-MMD contains 1076 long video sequences in 51 action categories, performed by 66 subjects in three camera views. It contains almost 20,000 action instances and 5.4 million frames in total. Our dataset also provides multimodality data sources, including RGB, depth, Infrared Radiation and Skeleton. With different modalities, we conduct extensive experiments on our dataset in terms of two scenarios and evaluate different methods by various metrics, including a new proposed evaluation protocol 2D-AP. We believe this large-scale dataset will benefit future researches on action detection for the community

MK-MMD（Maximum Mean Discrepancy）是一种用于度量两个概率分布之间距离的方法。它通过计算两个分布的特征空间中的样本均值之间的差异来衡量它们的相似性。MK-MMD常用于生成对抗网络（GANs）的训练中，其中生成器的目标是尽可能地模仿真实数据的分布。交叉熵损失函数是一种在分类任务中常用的损失函数。它用于衡量模型输出和真实标签之间的差异。交叉熵损失函数在训练过程中，通过最小化模型输出和真实标签之间的交叉熵来驱使模型逐渐收敛到正确的分类结果。

阅读全文