Dance experts often view dance as a hierarchy of information, spanning
low-level (raw images, image sequences), mid-levels (human poses and bodypart
movements), and high-level (dance genre). We propose a Hierarchical Dance Video
Recognition framework (HDVR). HDVR estimates 2D pose sequences, tracks dancers,
and then simultaneously estimates corresponding 3D poses and 3D-to-2D imaging
parameters, without requiring ground truth for 3D poses. Unlike most methods
that work on a single person, our tracking works on multiple dancers, under
occlusions. From the estimated 3D pose sequence, HDVR extracts body part
movements, and therefrom dance genre. The resulting hierarchical dance
representation is explainable to experts. To overcome noise and interframe
correspondence ambiguities, we enforce spatial and temporal motion smoothness
and photometric continuity over time. We use an LSTM network to extract 3D
movement subsequences from which we recognize the dance genre. For experiments,
we have identified 154 movement types, of 16 body parts, and assembled a new
University of Illinois Dance (UID) Dataset, containing 1143 video clips of 9
genres covering 30 hours, annotated with movement and genre labels. Our
experimental results demonstrate that our algorithms outperform the
state-of-the-art 3D pose estimation methods, which also enhances our dance
recognition performance.

提出了一种分层舞蹈视频识别框架 (HDVR)，它通过估计 2D 姿势序列，跟踪舞者，并同时估计相应的 3D 姿势和 3D 到 2D 成像参数来提取舞蹈的层次结构。我们在多人跟踪和通过 LSTM 网络识别舞蹈类型方面优于现有的 3D 姿势估计方法。

层次化舞蹈视频识别无监督 3D 姿态估计

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

Action recognition and human pose estimation are closely related but both
problems are generally handled as distinct tasks in the literature. In this
work, we propose a multitask framework for jointly 2D and 3D pose estimation
from still images and human action recognition from video sequences. We show
that a single architecture can be used to solve the two problems in an
efficient way and still achieves state-of-the-art results. Additionally, we
demonstrate that optimization from end-to-end leads to significantly higher
accuracy than separated learning. The proposed architecture can be trained with
data from different categories simultaneously in a seamlessly way. The reported
results on four datasets (MPII, Human3.6M, Penn Action and NTU) demonstrate the
effectiveness of our method on the targeted tasks.

本文提出了一种多任务框架，用于联合解决静态图像的二维和三维姿势估计及视频序列的人类动作识别问题。实现了端到端优化，与传统分开学习相比准确率显著提高，报告了使用该方法对 MPII、Human3.6M、Penn Action 和 NTU 四个数据集的测试结果，证明了其在目标任务上的有效性。

使用多任务深度学习进行 2D/3D 姿势估计和动作识别

2D/3D Pose Estimation and Action Recognition using Multitask Deep  Learning

Regression based methods are not performing as well as detection based
methods for human pose estimation. A central problem is that the structural
information in the pose is not well exploited in the previous regression
methods. In this work, we propose a structure-aware regression approach. It
adopts a reparameterized pose representation using bones instead of joints. It
exploits the joint connection structure to define a compositional loss function
that encodes the long range interactions in the pose. It is simple, effective,
and general for both 2D and 3D pose estimation in a unified setting.
Comprehensive evaluation validates the effectiveness of our approach. It
significantly advances the state-of-the-art on Human3.6M and is competitive
with state-of-the-art results on MPII.

提出了一种结构感知回归方法，利用骨代替节点进行重新参数化，使用联合连接结构定义组合损失函数来编码姿态中的长程相互作用，在 2D 和 3D 姿态估计中具有普适性并且在人体姿态估计领域的两个数据集（Human3.6M 和 MPII）中显著超越最先进的方法和竞争最先进结果的性能。