ASR-GCN:适应空间信息重建GCN用于基于骨架的动作识别
Ying Wu1, Zixuan Xu1, Yuchen Huang1
1School of Software, Yunnan University, Kunming, Yunnan, 650091, China.
概括
本研究介绍了一种基于骨架的动作识别的自适应空间信息重建模型 (ASR-GCN). 该模型增强了特征提取和动态学习,在基准数据集上实现了最先进的结果.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 基于骨的动作识别在计算机视觉中至关重要.
- 现有的方法在特征提取和动态学习中对复杂的动作进行斗争.
研究的目的:
- 提出一个创新的自适应空间信息重建模型 (ASR-GCN),以克服基于骨架的动作识别的局限性.
- 为了增强功能提取和动态功能学习能力.
主要方法:
- 开发了一个有门的重建单元 (GRU),用于代表性特征学习的重权重组策略.
- 构建了一个适应空间信息重建单元 (ASRU),用于适应特征贡献调整,提取,重权和集成.
主要成果:
- 该ASR-GCN模型显著提高了识别能力与最小的参数和计算开销.
- 在NTU RGB+D 60和NTU RGB+D 120数据集上实现了最先进的性能.
- 在跨主题任务中达到90.9%的准确率,在跨组任务中达到92.4%的准确率.
结论:
- 拟议的ASR-GCN模型有效地解决了基于骨架的动作识别方面的挑战.
- 适应性特征提取方法增强了对内在骨架数据特征的深度挖掘.
- 该模型在动作识别任务中表现出卓越的性能和效率.
相关概念视频
Assembly of Signaling Complexes
4.7K
Multiprotein signaling complexes are formed in a dynamic process involving protein-protein interactions at the cytoplasmic domain of transmembrane receptors or enzymatic and non-enzymatic proteins associated with the receptor. These complexes ensure the activation and propagation of intracellular signals that regulate cell functions.
Interaction domains in cell signaling
Interaction domains recognize exposed features of their binding partners containing post-translationally modified sequences,...
Interaction domains in cell signaling
Interaction domains recognize exposed features of their binding partners containing post-translationally modified sequences,...
4.7K
Classification of Bones
14.3K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
14.3K
Structural Classification of Joints
8.0K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
A fibrous joint is where the adjacent bones are united by fibrous connective...
8.0K
Centroid of a Body: Problem Solving
2.3K
The centroid of a body is a crucial concept in engineering and physics. Finding the centroid of a body can help determine its stability, its balance point, and even its design. In this context, consider a thin wire bent in the form of a quarter circular arc. Polar coordinates are used to calculate the centroid. The wire is first divided into small differential elements of a length equal to the radius multiplied by the differential angle.
The x-coordinates and y-coordinates of each element's...
The x-coordinates and y-coordinates of each element's...
2.3K
Spinal Cord: Information Processing
4.1K
The spinal cord is an integral hub for motor and sensory information that enables the brain to communicate with the peripheral nervous system (PNS). This communication consists of relaying sensory data and transmission of motor commands.
Sensory Information Processing
Sensory information processing begins at the sensory receptors located in the skin and other tissues, which detect somatic sensory stimuli such as touch, temperature, or pain. These receptors function as catalysts, initiating...
Sensory Information Processing
Sensory information processing begins at the sensory receptors located in the skin and other tissues, which detect somatic sensory stimuli such as touch, temperature, or pain. These receptors function as catalysts, initiating...
4.1K
State Space Representation
785
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
Consider an RLC circuit, a...
785


