Ensembled Transfer Learning Based Multichannel Attention Networks for Human Activity Recognition in Still Images

Hirooka, Koki; Hasan, Md. Al Mehedi; Shin, Jungpil; Srizon, Azmain Yakin

doi:10.1109/access.2022.3171263

Cited by 18 publications

(8 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It depicts the accuracy results of different deep learningbased models with various benchmark datasets, namely HII [27], HIIv2 [6] and our H2HId dataset. Among all the models considered for evaluation, the proposed model attained the topmost accuracy of 96.38% on the HII dataset, followed by the EfficientNet [22] and EnsembleNet [33] models with 95.83% and 95.37% accuracy, respectively. Our method demonstrated high classification performance on the two benchmark datasets, namely the HII and HIIv2, yielding remarkable accuracies.…”

Section: Results Analysismentioning

confidence: 99%

Recognition of Human Interactions in Still Images using AdaptiveDRNet with Multi-level Attention

Dey,

Biswas,

2023

IJACSA

View full text Add to dashboard Cite

Human-Human Interaction Recognition (H2HIR) is a multidisciplinary field that combines computer vision, deep learning, and psychology. Its primary objective is to decode and understand the intricacies of human-human interactions. H2HIR holds significant importance across various domains as it enables machines to perceive, comprehend, and respond to human social behaviors, gestures, and communication patterns. This study aims to identify human-human interactions from just one frame, i.e. from an image. Diverging from the realm of video-based interaction recognition, a well-established research domain that relies on the utilization of spatio-temporal information, the complexity of the task escalates significantly when dealing with still images due to the absence of these intrinsic spatio-temporal features. This research introduces a novel deep learning model called AdaptiveDRNet with Multi-level Attention to recognize Human-Human (H2H) interactions. Our proposed method demonstrates outstanding performance on the Human-Human Interaction Image dataset (H2HID), encompassing 4049 meticulously curated images representing fifteen distinct human interactions and on the publicly accessible HII and HIIv2 related benchmark datasets. Notably, our proposed model excels with a validation accuracy of 97.20% in the classification of human-human interaction images, surpassing the performance of EfficientNet, InceptionResNetV2, NASNet Mobile, ConvXNet, ResNet50, and VGG-16 models. H2H interaction recognition's significance lies in its capacity to enhance communication, improve decision-making, and ultimately contribute to the well-being and efficiency of individuals and society as a whole.

show abstract

Section: Results Analysismentioning

confidence: 99%

Recognition of Human Interactions in Still Images using AdaptiveDRNet with Multi-level Attention

Dey,

Biswas,

2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…Lastly, the feature maps which is extracted from 4 branches concatenated, and put into fully-connected network for producing the final recognition output. Hirooka et al [12] offer a new hybrid DL network for HAR which uses multi-modal sensor data, but this presented method was ConvLSTM pipeline which completely uses the data in every layer derived from the temporal domain. At last, a fully-connected layer and a softmax function were utilized for computing the probability of every class.…”

Section: Related Workmentioning

confidence: 99%

Fire Hawk Optimizer with Deep Learning Enabled Human Activity Recognition

Alonazi¹,

Alnfiai²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Human-Computer Interaction (HCI) is a sub-area within computer science focused on the study of the communication between people (users) and computers and the evaluation, implementation, and design of user interfaces for computer systems. HCI has accomplished effective incorporation of the human factors and software engineering of computing systems through the methods and concepts of cognitive science. Usability is an aspect of HCI dedicated to guaranteeing that human-computer communication is, amongst other things, efficient, effective, and sustaining for the user. Simultaneously, Human activity recognition (HAR) aim is to identify actions from a sequence of observations on the activities of subjects and the environmental conditions. The vision-based HAR study is the basis of several applications involving health care, HCI, and video surveillance. This article develops a Fire Hawk Optimizer with Deep Learning Enabled Activity Recognition (FHODL-AR) on HCI driven usability. In the presented FHODL-AR technique, the input images are investigated for the identification of different human activities. For feature extraction, a modified SqueezeNet model is introduced by the inclusion of few bypass connections to the SqueezeNet among Fire modules. Besides, the FHO algorithm is utilized as a hyperparameter optimization algorithm, which in turn boosts the classification performance. To detect and categorize different kinds of activities, probabilistic neural network (PNN) classifier is applied. The experimental validation of the FHODL-AR technique is tested using benchmark datasets, and the outcomes reported the improvements of the FHODL-AR technique over other recent approaches.

show abstract

“…To perform the activity recognition tasks from still images, some of the research focuses on using convolutional neural architectures which ensemble transfer learning-based multi-channel attention networks. The architecture has four CNN branches for feature fusion-based ensembling, with each branch having an attention module to extract contextual information from the pre-trained model's feature map [28]. In this paper, we leverage the advantages of transfer learning to propose a more accurate and less computationally complex sub-transfer learning model to boost the classification accuracies of the outlier subjects.…”

Section: Related Workmentioning

confidence: 99%

Sub-transfer Learning in Human Activity Recognition: Boosting the Outlier User Accuracy

Kanjilal¹,

Kucuk²,

Uysal³

2023

Preprint

View full text Add to dashboard Cite

<p>In this human activity recognition dataset, there are a total of 53 participants, consisting of 33 adults and 20 youths. In a laboratory experiment, individuals were given a set of synchronized sensors that were attached to their wrist and ankle using customized Velcro bands. These sensors, which were called Triaxial Wocket accelerometers, were lightweight, small, and thin. While wearing these sensors, the participants performed everyday tasks, and the raw acceleration data was collected at a rate of 90 Hz and transmitted wirelessly to a smartphone via Bluetooth.</p>

show abstract

Ensembled Transfer Learning Based Multichannel Attention Networks for Human Activity Recognition in Still Images

Cited by 18 publications

References 72 publications

Recognition of Human Interactions in Still Images using AdaptiveDRNet with Multi-level Attention

Recognition of Human Interactions in Still Images using AdaptiveDRNet with Multi-level Attention

Fire Hawk Optimizer with Deep Learning Enabled Human Activity Recognition

Sub-transfer Learning in Human Activity Recognition: Boosting the Outlier User Accuracy

Contact Info

Product

Resources

About