Effect of Motion-Gesture Recognizer Error Pattern on User Workload and Behavior

Katsuragawa, Keiko; Kamal, Ankit; Lank, Edward

doi:10.1145/3025171.3025234

Cited by 9 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They focus in particular on classifiers, and proposed a survey instrument to measure users' perception of accuracy. Both Kay et al and Katsuragawa et al noticed that different recognizers are perceived differently by users [8,9]. However, acceptable accuracy was only investigated in the context of automation with which user is passive [9], like notifications, or input recognition [8,16].…”

Section: Automated Tasks and Acceptable Accuracymentioning

confidence: 99%

“…Both Kay et al and Katsuragawa et al noticed that different recognizers are perceived differently by users [8,9]. However, acceptable accuracy was only investigated in the context of automation with which user is passive [9], like notifications, or input recognition [8,16]. Automated tasks were not considered, and usability only in the context of input recognition.…”

Section: Automated Tasks and Acceptable Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Automation Accuracy Is Good, but High Controllability May Be Better

Roy

Zhang

Vogel

2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

When automating tasks using some form of artificial intelligence, some inaccuracy in the result is virtually unavoidable. In many cases, the user must decide whether to try the automated method again, or fix it themselves using the available user interface. We argue this decision is influenced by both perceived automation accuracy and degree of task "controllability" (how easily and to what extent an automated result can be manually modified). This relationship between accuracy and controllability is investigated in a 750-participant crowdsourced experiment using a controlled, gamified task. With high controllability, self-reported satisfaction remained constant even under very low accuracy conditions, and overall, a strong preference was observed for using manual control rather than automation, despite much slower performance and regardless of very poor controllability.

show abstract

Section: Automated Tasks and Acceptable Accuracymentioning

confidence: 99%

Section: Automated Tasks and Acceptable Accuracymentioning

confidence: 99%

Automation Accuracy Is Good, but High Controllability May Be Better

Roy

Zhang

Vogel

2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Besides hand tracking, vision-based systems have been proposed for face tracking [23][24][25], action tracking [26][27][28] and gait tracking [29,30]. Although, the outcomes of the contemporary research works favour gesture-based interfaces for interactions [31,32], such systems are fairly more error-prone [33].…”

Section: Introductionmentioning

confidence: 99%

GIFT: Gesture-Based Interaction by Fingers Tracking, an Interaction Technique for Virtual Environment

Raees¹,

Ullah²

2019

IJIMAI

View full text Add to dashboard Cite

Three Dimensional (3D) interaction is the plausible human interaction inside a Virtual Environment (VE). The rise of the Virtual Reality (VR) applications in various domains demands for a feasible 3D interface. Ensuring immersivity in a virtual space, this paper presents an interaction technique where manipulation is performed by the perceptive gestures of the two dominant fingers; thumb and index. The two fingertip-thimbles made of paper are used to trace states and positions of the fingers by an ordinary camera. Based on the positions of the fingers, the basic interaction tasks; selection, scaling, rotation, translation and navigation are performed by intuitive gestures of the fingers. Without keeping a gestural database, the features-free detection of the fingers guarantees speedier interactions. Moreover, the system is user-independent and depends neither on the size nor on the color of the users' hand. With a case-study project; Interactions by the Gestures of Fingers (IGF) the technique is implemented for evaluation. The IGF application traces gestures of the fingers using the libraries of OpenCV at the back-end. At the front-end, the objects of the VE are rendered accordingly using the Open Graphics Library; OpenGL. The system is assessed in a moderate lighting condition by a group of 15 users. Furthermore, usability of the technique is investigated in games. Outcomes of the evaluations revealed that the approach is suitable for VR applications both in terms of cost and accuracy.

show abstract