From Emotion AI to Cognitive AI

Zhao, Guoying; Li, Yante; Xu, Qianru

doi:10.53941/ijndi0101006

Cited by 35 publications

(11 citation statements)

References 67 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distinguishing different genders of virtual hands or designing personalized virtual hands for VR applications may lead to a deeper investigation of users’ embodied cognition in future. Furthermore, it is suggested that implementing cognitive artificial intelligence in VR systems can make them capable of analyzing and making decisions like human users (Zhao et al , 2022), which can help import the cognition capability to systems for better interaction between people and VR.…”

Section: Discussionmentioning

confidence: 99%

Understanding the effects of hand design on embodiment in virtual reality

Zhang

Huang

Yang

et al. 2023

AIEDAM

View full text Add to dashboard Cite

Understanding user perceptions of interacting with the virtual world is one of the research focuses in recent years, given the rapid proliferation of virtual reality (VR) and driven to establish the metaverse. Users can generate a familiar connection between their bodies and the virtual world by being embodied in virtual hands, and hand representations can induce users’ embodiment in VR. The sense of embodiment represents the cognitive awareness of one's manifestation and includes three subcomponents: the sense of body ownership, agency and self-location. There is insufficient evidence in the literature about the effects of hand designs on the embodiment, especially based on studying its three subcomponents. This study investigates how virtual hand designs with five realism levels influence the three subcomponents of embodiment in VR. This research employs a self-report questionnaire commonly used in the literature to assess embodiment and evaluates agency and self-location by introducing implicit methods (intentional binding and proprioceptive measurement) derived from psychology. Besides, the objective data of eye tracking is used to explore the connection between embodiment and hand designs, and classifying participants’ eye tracking data to help analyze the link between embodiment and user attention. Overall, this research makes a major contribution through a systematic exploration of users’ embodied experience in VR and offers important evidence of the effects of virtual hand designs on body ownership, agency, and self-location, respectively. In addition, this study provides a valuable reference for further investigation of embodiment through implicit and objective methods, and practical design recommendations for virtual hand design in VR applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Understanding the effects of hand design on embodiment in virtual reality

Zhang

Huang

Yang

et al. 2023

AIEDAM

View full text Add to dashboard Cite

show abstract

“…On the one hand, based on the findings of this study, task performance has an impact on users’ feeling of control, and scholars have attempted to enhance work quality by improving task efficiency in CAD as a way to show better creative idea generation in the design process (Veisz et al , 2012). It is also proposed that introducing cognitive artificial intelligence to the system can allow the system itself to analyze and make decisions like users (Zhao et al , 2022), which can bring cognition capability to the system for the enhanced user experience. On the other hand, we examined changes in SoA with different translation modes and 2D interface types as measured by EEG data; additionally, EEG has been shown to provide insights into designers’ creative ideas (Liu et al , 2018; Jia and Zeng, 2021).…”

Section: Discussionmentioning

confidence: 99%

Evaluating the feeling of control in virtual object translation on 2D interfaces

Sun

Huang

et al. 2023

AIEDAM

View full text Add to dashboard Cite

Computer-aided design (CAD) plays an essential role in creative idea generation on 2D screens during the design process. In most CAD scenarios, virtual object translation is an essential operation, and it is commonly used when designers simulate their innovative solutions. The degrees of freedom (DoF) of virtual object translation modes have been found to directly impact users’ task performance and psychological aspects in simulated environments. Little is known in the existing literature about the sense of agency (SoA), which is a critical psychological aspect emphasizing the feeling of control, in translation modes on 2D screens during the design process. Hence, this study aims to assess users’ SoA in virtual object translation modes on mouse-based, touch-based, and handheld augmented reality (AR) interfaces through subjective and objective measures, such as self-report, task performance, and electroencephalogram (EEG) data. Based on our findings in this study, users perceived a greater feeling of control in 1DoF translation mode, which may help them come up with more creative ideas, than in 3DoF translation mode in the design process; additionally, the handheld AR interface offers less control feel, which may have a negative impact on design quality and creativity, as compared with mouse- and touch-based interfaces. This research contributes to the current literature by analyzing the association between virtual object translation modes and SoA, as well as the relationship between different 2D interfaces and SoA in CAD. As a result of these findings, we propose several design considerations for virtual object translation on 2D screens, which may enable designers to perceive a desirable feeling of control during the design process.

show abstract

“…Moreover, DCP-A can be extended into multi-task pruning. In the future, we will 1) consider more different guidance mechanisms with layer information [32,46,47,49,56,57,66], 2) introduce control strategies to enhance the model robustness [3,27,33,50,51,58], and 3) extend our approach to other complicated multi-task learning problems [1,23,34,59,65,67].…”

Section: Discussionmentioning

confidence: 99%

Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach

Cheng

Wang²,

Ma³

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Neural network pruning offers great prospects for facilitating the deployment of deep neural networks on computational resource limited devices. Neural architecture search (NAS) provides an efficient way to automatically seek appropriate neural architecture design for compressed model. It is observed that, for existing NAS-based pruning methods, there is usually a lack of layer information when searching the optimal neural architecture. In this paper, we propose a new NAS approach, namely, differentiable channel pruning method guided via attention mechanism (DCP-A), where the adopted attention mechanism is able to provide layer information to guide the optimization of the pruning policy. The training process is differentiable with Gumbel-softmax sampling, while parameters are optimized under a two-stage training procedure. The neural network block with the shortcut is dedicatedly designed, which is of help to prune the network not only on its width but also on its depth. Extensive experiments are performed to verify the applicability and superiority of the proposed method. Detailed analysis with visualization of the pruned model architecture shows that our proposed DCP-A learns explainable pruning policies.

show abstract

From Emotion AI to Cognitive AI

Cited by 35 publications

References 67 publications

Understanding the effects of hand design on embodiment in virtual reality

Understanding the effects of hand design on embodiment in virtual reality

Evaluating the feeling of control in virtual object translation on 2D interfaces

Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach

Contact Info

Product

Resources

About