Appearance and voice are essential factors impacting users’ affective preferences for humanoid robots. However, little is known about how the appearance and voice of humanoid robots jointly influence users’ affective preferences and visual attention. We conducted a mixed-design eye-tracking experiment to examine the multisensory integration effect of humanoid robot appearances and voices on users’ affective preferences and visual attention. The results showed that the combinations of affectively preferred voices and appearances attracted more affective preferences and shorter average fixation durations. The combinations of non-preferred voices and preferred appearances captured less affective preferences and longer fixation durations. The results suggest that congruent combinations of affectively preferred voices and appearances might motivate a facilitation effect on users’ affective preference and the depth of visual attention through audiovisual complements. Incongruent combinations of non-preferred voices and preferred appearances might stimulate an attenuation effect and result in less affective preferences and a deeper retrieval of visual information. Besides, the head attracted the most amount of visual attention regardless of voice conditions. This paper contributes to deepening the understanding of the multisensory integration effect on users’ affective preferences and visual attention and providing practical implications for designing humanoid robots satisfying users’ affective preferences.

We present the ASA Questionnaire, an instrument for evaluating human interaction with an artificial social agent (ASA), resulting from multi-year efforts involving more than 100 Intelligent Virtual Agent (IVA) researchers worldwide. It has 19 measurement constructs constituted by 90 items, which capture more than 80% of the constructs identified in empirical studies published in the IVA conference 2013--2018. This paper reports on construct validity analysis, specifically convergent and discriminant validity of initial 131 instrument items that involved 532 crowd-workers who were asked to rate human interaction with 14 different ASAs. The analysis included several factor analysis models and resulted in the selection of 90 items for inclusion in the long version of the ASA questionnaire. In addition, a representative item of each construct or dimension was selected to create a 24-item short version of the ASA questionnaire. Whereas the long version is suitable for a comprehensive evaluation of human-ASA interaction, the short version allows quick analysis and description of the interaction with the ASA. To support reporting ASA questionnaire results, we also put forward an ASA chart. The chart provides a quick overview of the agent profile.

Improving the accuracy of block adjustment with few or no ground control points (GCPs) is one of the core issues for satellite imagery high-precision mapping. The GaoFen-7 (GF-7) satellite laser altimeter system is the first Chinese formal spaceborne laser altimeter system, which is equipped with laser footprint cameras for the first time. Given the very high height accuracy and high planimetric accuracy of the instrument, this letter proposed an adjustment method of ZiYuan-3 (ZY-3) satellite imagery by integrating GF-7 laser altimetry data. The laser control points (LCPs) were automatically extracted according to the registration of the footprint images and stereo images. Furthermore, the combined adjustment was performed with the LCPs as the vertical control and horizontal constraint. The performance of the proposed method was evaluated by using 417 stereo scenes of ZY-3 images and 954 LCPs, covering an area of 158 000 km2in Shandong, China. The results demonstrated that, only by using all LCPs as the vertical control, the root mean square error (RMSE) of elevation can be significantly improved from the original 8.82 to 1.40 m. Moreover, the planimetric RMSE decreased from the original 15.31 to 3.58 m with residual randomness when 45 LCPs were used as the horizontal constraint. Our method provides an alternative solution for satellite imagery geopositioning improvement without GCPs.

In this paper, we report on the multi-year Intelligent Virtual Agents (IVA) community effort, involving more than 90 researchers worldwide, researching the IVA community interests and practice in evaluating human interaction with an artificial social agent (ASA). The joint efforts have previously generated a unified set of 19 constructs that capture more than 80% of constructs used in empirical studies published in the IVA conference between 2013 to 2018. In this paper, we present expert-content-validated 131 questionnaire items for the constructs and their dimensions, and investigate the level of reliability. We establish this in three phases. Firstly, eight experts generated 431 potential construct items. Secondly, 20 experts rated whether items measure (only) their intended construct, resulting in 207 content-validated items. Next, a reliability analysis was conducted, involving 192 crowd-workers who were asked to rate a human interaction with an ASA, which resulted in 131 items (about 5 items per measurement, with Cronbach's alpha ranged [.60 -- .87]). These are the starting points for the questionnaire instrument of human-ASA interaction.

Affective computing focuses on technologies and theories that advance understanding of human affect, considering emotion and cognition in the design of related technologies to fulfill human needs, which gains substantial attention of researchers all over the world. To provide an insight into affective computing researches, this paper utilizes the method of bibliometric analysis to obtain information with respect to when and where the researches were performed by whom and how the mainstream contents evolved over the years. BibExcel and CiteSpace were employed to conduct the performance analysis and co-citation network analysis, including the analysis of the performance of countries, journals, institutes, authors and research hotspots. A total number of 1,625 documents published from 1999 ~ 2018 were screened to conduct quantitative analysis, which were retrieved in the Web of Science database with defined search terms. This paper can enable researchers to gain wider and deeper insight into affective computing researches in the last decades through bibliometric analysis, thereby facilitating relevant researchers having a general understanding of aggregate performance in the affective computing field and finding research directions in the future.

Traffic congestion estimation in arterial networks with sparse GPS probe data is a practically important while substantially challenging research issue. The effectiveness and efficiency of the existing GPS probe data-based traffic estimation models are largely limited due to the following two challenges. First, due to the low sampling frequency of GPS probes, probe data are usually sparse, especially for some road links not located in the central urban areas. Second, due to the very complex temporal and spatial dependencies among the road links, the variable space of the existing traffic estimation models is huge. It is time consuming to get an accurate estimation of a large arterial road network with thousands of road links. To address the above-mentioned issues, this paper proposes to extract traffic event signals from social media and incorporate them with GPS probe data to alleviate the data sparse issue. We first collect traffic-related posts that report various traffic events, including traffic jam, accident, and road construction from Twitter. By considering the GPS probe readings and the traffic event tweets as two types of observations, we next extend the conventional coupled hidden Markov model for integrating the two types of data to obtain a more accurate estimation of traffic conditions. To address the computational challenge, a parallel importance sampling-based electromagnetic algorithm is further introduced. We evaluate our model on the arterial network of downtown Chicago. The experimental results demonstrate the superior performance of the model in both effectiveness and efficiency.