论文阅读 [TPAMI-2022] Coherence Constrained Graph LSTM for Group Activity Recognition

论文阅读 [TPAMI-2022] Coherence Constrained Graph LSTM for Group Activity Recognition

论文搜索(studyai.com)

搜索论文: Coherence Constrained Graph LSTM for Group Activity Recognition

搜索论文: http://www.studyai.com/search/whole-site/?q=Coherence+Constrained+Graph+LSTM+for+Group+Activity+Recognition

关键字(Keywords)

Coherence; Activity recognition; Logic gates; Motion measurement; Time measurement; Recurrent neural networks; Games; Group activity recognition; long short-term memory; fine-grained motion; deep learning

机器学习; 机器视觉

细粒度视觉; 递归神经网络; 群体活动识别; 时间与空间; 注意力机制

摘要(Abstract)

This work aims to address the group activity recognition problem by exploring human motion characteristics.

这项工作旨在通过探索人体运动特征来解决群体活动识别问题。.

Traditional methods hold that the motions of all persons contribute equally to the group activity, which suppresses the contributions of some relevant motions to the whole activity while overstating some irrelevant motions.

传统方法认为，所有人的动作对集体活动的贡献是相等的，这会抑制一些相关动作对整个活动的贡献，同时夸大一些不相关的动作。.

To address this problem, we present a Spatio-Temporal Context Coherence (STCC) constraint and a Global Context Coherence (GCC) constraint to capture the relevant motions and quantify their contributions to the group activity, respectively.

为了解决这个问题，我们分别提出了时空上下文一致性（STCC）约束和全局上下文一致性（GCC）约束来捕获相关运动并量化它们对群体活动的贡献。.

Based on this, we propose a novel Coherence Constrained Graph LSTM (CCG-LSTM) with STCC and GCC to effectively recognize group activity, by modeling the relevant motions of individuals while suppressing the irrelevant motions.

在此基础上，我们提出了一种新的相干约束图LSTM（CCG-LSTM），结合STCC和GCC，通过对个体的相关运动建模，同时抑制无关运动，有效地识别群体活动。.

Specifically, to capture the relevant motions, we build the CCG-LSTM with a temporal confidence gate and a spatial confidence gate to control the memory state updating in terms of the temporally previous state and the spatially neighboring states, respectively.

具体来说，为了捕捉相关运动，我们构建了CCG-LSTM，其中包含一个时间置信门和一个空间置信门，分别根据时间上的前一个状态和空间上的相邻状态来控制内存状态的更新。.

In addition, an attention mechanism is employed to quantify the contribution of a certain motion by measuring the consistency between itself and the whole activity at each time step.

此外，注意机制被用来量化某个运动的贡献，通过测量其自身和每个时间步的整个活动之间的一致性。.

Finally, we conduct experiments on two widely-used datasets to illustrate the effectiveness of the proposed CCG-LSTM compared with the state-of-the-art methods…

最后，我们在两个广泛使用的数据集上进行了实验，以说明所提出的CCG-LSTM与最先进的方法相比的有效性。。.

作者(Authors)

[‘Jinhui Tang’, ‘Xiangbo Shu’, ‘Rui Yan’, ‘Liyan Zhang’]