Unsupervised Extraction of Human-Interpretable Nonverbal Behavioral Cues in a Public Speaking Scenario

Tanveer, Md. Iftekhar; Ji, Liu; Hoque, Mohammed Ehsan

doi:10.1145/2733373.2806350

Cited by 14 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the value of the objective function increases at any iteration, the step size is largely penalized (by 50 percent decrease) because it indicates the step size is too large. We find in empirical tests that bold driver is faster to perform than a typical Line Search approach, described by Tanveer et al [35]. In addition, it takes a lower number of iterations than a constant step size.…”

Section: Speedup Techniquesmentioning

confidence: 68%

“…Zhou et al [40] proposed Aligned Cluster Analysis (ACA), which detects patterns in signals using k-means clustering and dynamic time warping. Tanveer et al [35] proposed a sparse coding based approach for detecting common behavioral cues for body language. In this paper, we use the method mentioned in Tanveer and useful recommendations should be effectively and intuitively conveyed to the users.…”

Section: Automated Assessment Of Public Speaking Competencementioning

confidence: 99%

“…[16,37] In this paper, we disregard the aspect of "meaning" for behavioral cues and use it interchangeably as "body movement patterns." In our prior research [35], we proposed an unsupervised algorithm to extract human-interpretable patterns of body movements from MoCap signals. Our algorithm was inspired by the Shift Invariant Sparse Coding (SISC) algorithm, proposed by Morup et al [21].…”

Section: Extracting the Behavioral Cuesmentioning

confidence: 99%

“…We briefly describe the technique in this section. Please refer to Tanveer et al [35] for an elaborate discussion of this algorithm.…”

Section: Extracting the Behavioral Cuesmentioning

confidence: 99%

“…In one of our previous projects [35], we proposed a sparsitybased algorithm to extract repetitive body movements (behavioral cues). In the AutoManner interface, we use this algorithm to automatically extract and show these repetitive movements to the speaker.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

AutoManner

Tanveer

Zhao

Chen

et al. 2016

Proceedings of the 21st International Conference on Intelligent User Interfaces

Self Cite

View full text Add to dashboard Cite

Many individuals exhibit unconscious body movements called mannerisms while speaking. These repeated changes often distract the audience when not relevant to the verbal context. We present an intelligent interface that can automatically extract human gestures using Microsoft Kinect to make speakers aware of their mannerisms. We use a sparsitybased algorithm, Shift Invariant Sparse Coding, to automatically extract the patterns of body movements. These patterns are displayed in an interface with subtle question and answerbased feedback scheme that draws attention to the speaker's body language. Our formal evaluation with 27 participants shows that the users became aware of their body language after using the system. In addition, when independent observers annotated the accuracy of the algorithm for every extracted pattern, we find that the patterns extracted by our algorithm is significantly (p < 0.001) more accurate than just random selection. This represents a strong evidence that the algorithm is able to extract human-interpretable body movement patterns. An interactive demo of AutoManner is available at http://tinyurl.com/AutoManner.

show abstract

Section: Speedup Techniquesmentioning

confidence: 68%

Section: Automated Assessment Of Public Speaking Competencementioning

confidence: 99%