Ambient intelligence-based multimodal human action recognition for autonomous systems

Jain, Vidhi; Gupta, Gourav; Gupta, Megha; Sharma, Deepak Kumar; Ghosh, Uttam

doi:10.1016/j.isatra.2022.10.034

Cited by 12 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model also adopts a hierarchical fusion strategy and uses a uniform spatio-temporal loss for overall training, which also achieves good results. Jain et al [32] Structure of the two-stream network model.…”

Section: Based On Dual/multistream Network and Their Variantsmentioning

confidence: 99%

An Overview of Behavioral Recognition

Xie,

Xiang,

et al. 2024

ITC

View full text Add to dashboard Cite

Human behavior recognition has become a popular research topic in the field of computer vision. With the introduction of deep learning and attention mechanisms, this field has been further promoted. However, issues such as dataset acquisition and preprocessing operations on multimodal datasets, modeling of long time information in videos, and fusion of temporal and spatial information still exist. In this paper, we first outline some video action recognition datasets and related preprocessing techniques, including frame extraction, optical flow extraction, and skeletal feature acquisition. Then, the relevant models are classified and parsed according to their characteristics and the types of input data modalities. In addition, we evaluate the performance of the models on several benchmark datasets to gain a deeper understanding of the model development process. Finally, we summarized the current challenges faced in the field of video behavior recognition, including model timeliness, data set subjectivity and effective fusion of multi-modal features, and proposed possible future improvement directions in order to provide more ideas and methods for subsequent research.

show abstract

Section: Based On Dual/multistream Network and Their Variantsmentioning

confidence: 99%

An Overview of Behavioral Recognition

Xie,

Xiang,

et al. 2024

ITC

View full text Add to dashboard Cite

show abstract

“…HAR refers to the process of recognizing and understanding human actions, which is essential for various real-world applications, such as assisted living [10], visual surveillance [11], autonomous navigation [12], video retrieval [13], human-robot interaction [14,15], and entertainment [16]. The concept of HAR encompasses various aspects, including action recognition, intention understanding, and narrative understanding [17,18].…”

Section: General Background On Harmentioning

confidence: 99%

Review on Human Action Recognition in Smart Living: Sensing Technology, Multimodality, Real-Time Processing, Interoperability, and Resource-Constrained Processing

Diraco

Rescio

Siciliano

et al. 2023

Sensors

View full text Add to dashboard Cite

Smart living, a concept that has gained increasing attention in recent years, revolves around integrating advanced technologies in homes and cities to enhance the quality of life for citizens. Sensing and human action recognition are crucial aspects of this concept. Smart living applications span various domains, such as energy consumption, healthcare, transportation, and education, which greatly benefit from effective human action recognition. This field, originating from computer vision, seeks to recognize human actions and activities using not only visual data but also many other sensor modalities. This paper comprehensively reviews the literature on human action recognition in smart living environments, synthesizing the main contributions, challenges, and future research directions. This review selects five key domains, i.e., Sensing Technology, Multimodality, Real-time Processing, Interoperability, and Resource-Constrained Processing, as they encompass the critical aspects required for successfully deploying human action recognition in smart living. These domains highlight the essential role that sensing and human action recognition play in successfully developing and implementing smart living solutions. This paper serves as a valuable resource for researchers and practitioners seeking to further explore and advance the field of human action recognition in smart living.

show abstract

“…Ultimately, the goal is to develop a personalized learning strategy. Other more recent studies on AmI include the following: investigating human action recognition for autonomous systems [60], identification of pathways towards the realization of AmI utilizing task-oriented sensing at the edge of computing [61], language learning [62], and the metaverse [63]. However, research studies in the area of education are lacking.…”

Section: Emerging Artificial Intelligence and Promise For The Educati...mentioning

confidence: 99%

Challenges and Opportunities in the Internet of Intelligence of Things in Higher Education—Towards Bridging Theory and Practice

Saadé,

Zhang,

Wang

et al. 2023

IoT

View full text Add to dashboard Cite

The application of the Internet of Things is increasing in momentum as advances in artificial intelligence exponentially increase its integration. This has caused continuous shifts in the Internet of Things paradigm with increasing levels of complexity. Consequently, researchers, practitioners, and governments continue facing evolving challenges, making it more difficult to adapt. This is especially true in the education sector, which is the focus of this article. The overall purpose of this study is to explore the application of IoT and artificial intelligence in education and, more specifically, learning. Our methodology follows four research questions. We first report the results of a systematic literature review on the Internet of Intelligence of Things (IoIT) in education. Secondly, we develop a corresponding conceptual model, followed thirdly by an exploratory pilot survey conducted on a group of educators from around the world to get insights on their knowledge and use of the Internet of Things in their classroom, thereby providing a better understanding of issues, such as knowledge, use, and their readiness to integrate IoIT. We finally present the application of the IoITE conceptual model in teaching and learning through four use cases. Our review of publications shows that research in the IoITE is scarce. This is even more so if we consider its application to learning. Analysis of the survey results finds that educators, in general, are lacking in their readiness to innovate with the Internet of Things in learning. Use cases highlight IoITE possibilities and its potential to explore and exploit. Challenges are identified and discussed.

show abstract

Ambient intelligence-based multimodal human action recognition for autonomous systems

Cited by 12 publications

References 3 publications

An Overview of Behavioral Recognition

An Overview of Behavioral Recognition

Review on Human Action Recognition in Smart Living: Sensing Technology, Multimodality, Real-Time Processing, Interoperability, and Resource-Constrained Processing

Challenges and Opportunities in the Internet of Intelligence of Things in Higher Education—Towards Bridging Theory and Practice

Contact Info

Product

Resources

About