Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions

Zhang, Zufan; Lv, Zongming; Gan, Chenquan; Zhu, Qingyi

doi:10.1016/j.neucom.2020.06.032

Cited by 80 publications

(54 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several traditional sequential learning forecasting models have been developed for energy consumption forecasting that reveal inadequate performance due to the utilization of unclean data. These approaches face various problems while learning parameters from scratch, such as overfitting, and short-term memory difficulties, such as data increases or the association between variables, become more complex [41]. These problems can be easily tackled through sequential learning models that have the ability to capture spatial and temporal patterns from smart meters data at once.…”

Section: Proposed Frameworkmentioning

confidence: 99%

Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors

et al. 2021

View full text Add to dashboard Cite

The use of electrical energy is directly proportional to the increase in global population, both concerning growing industrialization and rising residential demand. The need to achieve a balance between electrical energy production and consumption inspires researchers to develop forecasting models for optimal and economical energy use. Mostly, the residential and industrial sectors use metering sensors that only measure the consumed energy but are unable to manage electricity. In this paper, we present a comparative analysis of a variety of deep features with several sequential learning models to select the optimized hybrid architecture for energy consumption prediction. The best results are achieved using convolutional long short-term memory (ConvLSTM) integrated with bidirectional long short-term memory (BiLSTM). The ConvLSTM initially extracts features from the input data to produce encoded sequences that are decoded by BiLSTM and then proceeds with a final dense layer for energy consumption prediction. The overall framework consists of preprocessing raw data, extracting features, training the sequential model, and then evaluating it. The proposed energy consumption prediction model outperforms existing models over publicly available datasets, including Household and Korean commercial building datasets.

show abstract

Section: Proposed Frameworkmentioning

confidence: 99%

Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Zhang et al [79] proposed a spatio-temporal dual attention network (STDAN) based on LSTM. Since each frame in the video may not provide equally important information, it is necessary to selectively focus on the frames containing important information to improve action recognition.…”

Section: Long Short-term Memory Networkmentioning

confidence: 99%

A Systematic Survey on Human Behavior Recognition Methods

et al. 2021

View full text Add to dashboard Cite

Human behavior is an essential component of social interaction and is of great significance to identify and analyze human behaviors in a variety of fields. Due to the rapid development of computer vision and machine learning technology, machine with intelligence has started replacing human beings to observe, perceive and analyze the explosive growth of image and video data. Computer vision and machine learning-based human behavior recognition is one of these tasks, which has become a particularly hot research topic in many different fields, such as intelligent monitoring, human-computer interaction, smart home, virtual reality, and medical diagnosis. In this study, we survey systematically the popular methods, algorithms, models and well-known action datasets in human behavior analysis in the past two decades. In addition, the advantages and disadvantages of the methods are discussed and propitious future research directions are also presented. The results of this survey reveal that paradigms of human behavior analysis is being shifted from traditional RGB to RGB-D, from deep learning to more intelligent and automated deep reinforcement learning, and from fixed camera devices to portable devices and channel state information (CSI), and paradigms based on automated deep reinforcement learning and portable devices and CSI would become some hot topics for future research on human behavior analysis.

show abstract

“…Gemmule H et al [25] focused on learning salient spatial features using a CNN and then mapped their temporal relationship with the aid of LSTM networks. Zufan Zhang et al [26] addressed the human action recognition issue by using a Conv-LSTM and fully connected LSTM with different attentions. However, convolutional neural networks demonstrated their superiority in both accuracy and parallelism [27][28][29].…”

Section: Related Workmentioning

confidence: 99%

Dual Attention-Guided Multiscale Dynamic Aggregate Graph Convolutional Networks for Skeleton-Based Human Action Recognition

Lee

2020

Symmetry

View full text Add to dashboard Cite

Traditional convolution neural networks have achieved great success in human action recognition. However, it is challenging to establish effective associations between different human bone nodes to capture detailed information. In this paper, we propose a dual attention-guided multiscale dynamic aggregate graph convolution neural network (DAG-GCN) for skeleton-based human action recognition. Our goal is to explore the best correlation and determine high-level semantic features. First, a multiscale dynamic aggregate GCN module is used to capture important semantic information and to establish dependence relationships for different bone nodes. Second, the higher level semantic feature is further refined, and the semantic relevance is emphasized through a dual attention guidance module. In addition, we exploit the relationship of joints hierarchically and the spatial temporal correlations through two modules. Experiments with the DAG-GCN method result in good performance on the NTU-60-RGB+D and NTU-120-RGB+D datasets. The accuracy is 95.76% and 90.01%, respectively, for the cross (X)-View and X-Subon the NTU60dataset.

show abstract

Human action recognition using convolutional LSTM and fully-connected LSTM with different attentions

Cited by 80 publications

References 15 publications

Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors

Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors

A Systematic Survey on Human Behavior Recognition Methods

Dual Attention-Guided Multiscale Dynamic Aggregate Graph Convolutional Networks for Skeleton-Based Human Action Recognition

Contact Info

Product

Resources

About