Abstract: In this paper, we propose a novel multimodal fusion framework, named locally confined modality fusion network (LMFN), that contains a bidirectional multiconnected LSTM (BM-LSTM) to address the multimodal human affective computing problem. Instead of conducting fusion only on a holistic level, we propose a hierarchical fusion strategy that considers both local and global interactions […]

Abstract: This paper describes an exploratory usability study designed to investigate how college students locate information in a Learning Management System and to establish a set of guidelines for creating the best course layouts that can increase the student’s learning experience. Using observations, perception survey data, and a high-fidelity eye-tracker that recorded where participants’ eyes […]

Abstract: Can the magnitude of the calorie distance between food items explain the contradictory findings in previous literature regarding the impact of calorie labeling laws? Our theoretical model suggests that the relative calorie difference between alternatives in food menus is a missing link important for understanding the impact of calorie labeling information on calorie intake […]

Abstract: We propose a general strategy named ‘divide, conquer and combine’ for multimodal fusion. Instead of directly fusing features at holistic level, we conduct fusion hierarchically so that both local and global interactions are considered for a comprehensive interpretation of multimodal embeddings. In the ‘divide’ and ‘conquer’ stages, we conduct local fusion by exploring the […]

Abstract: Background In general, people are poor at detecting deception. Older adults are even worse than young adults at detecting deceit, which might make them uniquely vulnerable to certain types of financial fraud. One reason for poor deceit detection abilities is that lay theories of cues to deception are not valid. This study compared the […]

Abstract: This paper learns multi-modal embeddings from text, audio, and video views/modes of data in order to improve upon downstream sentiment classification. The experimental framework also allows investigation of the relative contributions of the individual views in the final multi-modal embedding. Individual features derived from the three views are combined into a multi-modal embedding using […]

Abstract: Learning how architecture impacts human perception can help us understand how civic monuments bring us together or drive us apart, create community cohesion and identity or the reverse: anomie, placelessness and the fragmentation of the public realm. Boston City Hall and Plaza, an urban renewal project from the 1960s, intended to revitalize a historic […]

Abstract: Across two studies, we theorize and empirically investigate passion as a moderator of the negative affective consequences of fear of failure in early-stage entrepreneurship. We test our hypotheses in two field studies of naturally occurring affective events—namely, pitching competitions—and we complement self-reported measures of negative affect with physio-psychological measures obtained from analyzing entrepreneurs’ facial […]

Abstract: There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these concerns, we present a regularization method based on tensor rank minimization. Our […]

Abstract: The Emotional Domotics (home automation) is a concept that has been one of the main focus of our research team seeks to integrate the subject or user of an inhabitable space as central element for the modulation and control of the environmental variables in a house automation implementation for the life quality improvement and […]