Search

Presenting an idea is a critical social interaction, especially in a startup funding pitch setting where initial investment is at stake. Understanding a listener’s facial expression can then become extremely valuable in informing the level of engagement reached by the presenter. Predicting engagement level in other settings, such as an online study environment, has been explored in previous research, but none have explored to what extent an investor’s facial expression can predict the investor’s engagement during a funding pitch and in return predict the investor’s probability to invest. In this study, we propose to use Long Short-Term Memory (LSTM) networks along with facial action units (AUs), facial features extracted with Convolutional Neural Networks (CNN), and the combination of both as features for automated prediction of probability of investment. The results show a promising prospect for the proposed LSTM models. Models using CNN features or combined AU and CNN features outperformed the AU-only model.

Acquiring funding for a startup venture often involves pitching a business idea to potential investors. Insight into the nonverbal behavioral cues that impact the investment decision making process can help entrepreneurs to improve their persuasion skills and can provide valuable insights to investors and researchers. Previous re- search on the prediction of investment decisions in entrepreneurial pitches has primarily focused on analyzing (usually unimodal) behavioral cues from pitchers only. To address this gap, in this study we compare the predictive performance of different feature sets consisting of nonverbal behavior cues from different modalities (i.e., facial expressions, head movement, and vocal expressions) from both pitchers and investors and their self-reported characteristics. Our findings show promising results for the prediction of investor’s evaluations of entrepreneurial pitches. Multimodal behavioral cues, especially head movement and vocal expressions, were found to be most predictive.

Medical image-to-image translation, using conditional Gen-erative Adversarial Networks (cGANs), could be beneficial for clinicaldecisions when additional diagnostics scans are requested. The recentlyproposed pix2pix architecture provides an effective image-to-image trans-lation method to study such medical use of cGANs. This study addressesthe question to what extent pix2pix can translate a magnetic resonanceimaging (MRI) scan of a patient into an estimate of a positron emissiontomography (PET) scan of the same patient. We perform two image-to-image translation experiments using paired MRI and PET brain scansof Alzheimer’s disease patients and healthy controls. In experiment 1, wetrain using data sliced in one dimension (the axial plane). In experiment2, we train using augmented data sliced in all three dimensions (axial,sagittal and coronal). After training, the synthetically generated PETscans are compared to the actual ones. The results suggest that PETscans can be sufficiently and reliably estimated from MRI, with similarresults using axial and augmented training. We conclude that image-to-image translation is a promising and potentially cost-saving method formaking informed use of expensive diagnostic technology

Touch behavior is of great importance during social interaction. To transfer the tactile modality from interpersonal interaction to other areas such as Human-Robot Interaction (HRI) and remote communication automatic recognition of social touch is necessary. This paper introduces CoST: Corpus of Social Touch, a collection containing 7805 instances of 14 different social touch gestures. The gestures were performed in three variations: gentle, normal and rough, on a sensor grid wrapped around a mannequin arm. Recognition of the rough variations of these 14 gesture classes using Bayesian classifiers and Support Vector Machines (SVMs) resulted in an overall accuracy of 54% and 53%, respectively. Furthermore, this paper provides more insight into the challenges of automatic recognition of social touch gestures, including which gestures can be recognized more easily and which are more difficult to recognize.