(Press-News.org)
In a significant advancement for robotics and artificial intelligence, researchers at Chongqing University of Technology, along with their international collaborators, have developed a cutting-edge method for enhancing interaction recognition. The study, published in Cyborg and Bionic Systems, introduces the Merge-and-Split Graph Convolutional Network (MS-GCN), a novel approach specifically designed to address the complexities of skeleton-based interaction recognition.
Human interaction recognition plays a crucial role in various applications, ranging from enhancing human-computer interfaces to improving surveillance systems. Traditional methods, typically reliant on RGB data, struggle with issues like illumination changes and occlusions, making accurate recognition a challenge. Skeleton-based methods, which focus on the structure of human joints, provide a promising alternative due to their robustness against such environmental variations.
The newly introduced MS-GCN tackles the longstanding problem of capturing interaction dynamics between multiple individuals, which has often been overlooked by conventional graph convolution networks. By integrating Merge-and-Split Graph Convolution with Hierarchical Guided Attention and a Short-term Dependence module, the MS-GCN excels at understanding the nuanced relationships between different body parts during interactions.
Innovative Features of MS-GCN:
Merge-and-Split Graph Structure: This structure uniquely merges the joint information of interacting individuals into a unified feature space, allowing for a holistic analysis of interactions. It maps the nodes of corresponding hierarchical sets of two individuals in the same semantic space, facilitating more precise recognition of interaction-specific movements.
Hierarchical Guided Attention: This component is pivotal in emphasizing the importance of different hierarchical sets based on their relevance to the interaction at hand. For instance, in actions like hand waving, it focuses more on the hierarchical sets that involve the hands, ensuring that critical motion characteristics are not missed.
Short-term Dependence Module: Recognizing that short-term variations in motion can be critical for distinguishing between similar actions, such as a handshake and a high-five, this module enhances the model's sensitivity to these subtle differences.
The effectiveness of the MS-GCN is underscored by its performance on two recognized datasets, NTU60 and NTU120, where it achieved state-of-the-art results. The approach has been rigorously validated through extensive experiments, demonstrating its superiority over existing methods in both dual-person and individual interaction scenarios.
The implications of this research are profound. As robots and AI systems become increasingly integrated into daily life, their ability to understand and interact with humans in a nuanced and meaningful way is paramount. The MS-GCN not only advances the field of action recognition but also opens new avenues for the development of more intuitive and responsive AI systems.
This breakthrough underscores a significant step forward in the quest for AI that can seamlessly integrate into human environments, offering a glimpse into a future where digital systems can anticipate and respond to human actions with unprecedented accuracy and efficiency.
The paper, " Merge-and-Split Graph Convolutional Network for Skeleton-Based Interaction Recognition," was published in the journal Cyborg and Bionic Systems on Mar 20, 2024, at DOI: https://spj.science.org/doi/10.34133/cbsystems.0102
END
Endowed with the power of memory, certain alloys can magically return to their original shape when heated or deformed. However, the repeated back-and-forth between the original and new configuration may leave permanent imprints on the alloy’s microscopic features, which could then impact its ability to reversibly transform shape. Thus, unraveling the impact of the strain history on these alloys’ functionality is essential to improving predictive capabilities, but it has not received enough attention.
To fill this knowledge gap, the National Science Foundation ...
The electromagnetic driving systems are proposed for the flexible 5-DOF magnetic manipulation of a micro-robot within the posterior eye, enabling precise targeted drug delivery. A research team has presented a novel electromagnetic driving system that consists of eight optimized electromagnets arranged in an optimal configuration and employs a control framework based on an active disturbance rejection controller (ADRC) and virtual boundary.
The team published their findings in Cyborg and Bionic Systems on Mar 23, 2024.
Intraocular microsurgery has witnessed a transition from the utilization of conventional handheld surgical tools to the adoption of robot-assisted surgery, owing ...
New York, NY [May 31, 2024]—Researchers at the Icahn School of Medicine at Mount Sinai and others have identified a neurodevelopmental disorder, caused by mutations in a single gene, that affects tens of thousands of people worldwide. The work, published in the May 31 online issue of Nature Medicine [DOI: 10.1038/s41591-024-03085-5], was done in collaboration with colleagues at the University of Bristol, UK; KU Leuven, Belgium; and the NIHR BioResource, currently based at the University of Cambridge, UK.
The findings will improve clinical diagnostic ...
Losing a loved one to drug overdose has been a common experience for many Americans in recent years, crossing political and socioeconomic divides and boosting the perceived importance of the overdose crisis as a policy issue, according to a new survey led by researchers at the Johns Hopkins Bloomberg School of Public Health.
A nationally representative survey of more than 2,300 Americans, fielded in spring 2023, suggests that 32 percent of the U.S. adult population, or an estimated 82.7 million individuals, has lost someone they know to a fatal drug overdose. ...
About The Study: Higher adherence to the Mediterranean diet was associated with a 23% lower risk of all-cause mortality in this cohort study. This inverse association was partially explained by multiple cardiometabolic factors.
Corresponding Author: To contact the corresponding author, Shafqat Ahmad, Ph.D., email shafqat.ahmad@medsci.uu.se.
To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/
(doi:10.1001/jamanetworkopen.2024.14322)
Editor’s Note: Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest ...
Some 13% of older adults are diagnosed with traumatic brain injury (TBI), according to a study by UC San Francisco and the San Francisco VA Health Care System. These injuries are typically caused by falls from ground level.
Researchers followed about 9,200 Medicare enrollees, whose average age was 75 at the start of the study, and found that contrary to other studies of younger people, being female, white, healthier and wealthier was associated with higher risk of TBI.
The study publishes in JAMA Network Open on May 31, 2024.
The researchers, ...
A new study using stem cell-based models has shed new light on how the human embryo begins to develop, which could one day benefit the development of fertility treatment.
The study led by at the University of Exeter Living Systems Institute has revealed how early embryo cells decide between contributing to the foetus or to the supporting yolk sac.
Understanding this decision is important because the yolk sac is essential for later development in the womb. Producing the right number of yolk sac forming cells may be critical for infertility treatment using in vitro fertilised (IVF) embryos.
Only limited research ...
EMBARGOED by JAMA Network Open until 11 a.m., ET May 31, 2024
Contact: Maria Ober, mpober@bu.edu
BU Study Finds Policy Makers’ Use of In-Hospital Mortality as a Sepsis Quality Metric May Unfairly Penalize Safety-net Hospitals
(Boston)—Sepsis is a leading cause of death and disability and a key target of state and federal quality measures for hospitals. In-hospital mortality of patients with sepsis is frequently measured for benchmarking, both by researchers and policymakers. For example, in New York, sepsis regulations mandate reporting of risk-adjusted in-hospital mortality, and hospitals with lower or higher than expected in-hospital ...
Investigators from Brigham and Women’s Hospital identified and assessed underlying mechanisms that may explain the Mediterranean diet’s 23 percent reduction in all-cause mortality risk for American women
The health benefits of the Mediterranean diet have been reported in multiple studies, but there is limited long-term data of its effects in U.S. women and little understanding about why the diet may reduce risk of death. In a new study that followed more than 25,000 initially healthy U.S. women for up ...
By Alistair Jones
SMU Office of Research - If you dread public speaking you are not alone. It is a leading social phobia, one that can cause a state of anxiety that reduces otherwise articulate people to nervous incoherence.
A strong fear of public speaking is known as glossophobia. Academic studies estimate it affects 20 per cent of the population, but depending on the sample and methodology, the figure could be as high as 40 per cent.
As American writer and humourist Mark Twain said, ...
