In this paper we introduce a novel dataset, the Multimodal Human-Human-Robot-Interactions (MHHRI) dataset, with the aim of studying personality simultaneously in human-human interactions (HHI) and ...human-robot interactions (HRI) and its relationship with engagement. Multimodal data was collected during a controlled interaction study where dyadic interactions between two human participants and triadic interactions between two human participants and a robot took place with interactants asking a set of personal questions to each other. Interactions were recorded using two static and two dynamic cameras as well as two biosensors, and meta-data was collected by having participants fill in two types of questionnaires, for assessing their own personality traits and their perceived engagement with their partners (self labels) and for assessing personality traits of the other participants partaking in the study (acquaintance labels). As a proof of concept, we present baseline results for personality and engagement classification. Our results show that (i) trends in personality classification performance remain the same with respect to the self and the acquaintance labels across the HHI and HRI settings; (ii) for extroversion, the acquaintance labels yield better results as compared to the self labels; (iii) in general, multi-modality yields better performance for the classification of personality traits.
Engagement is crucial to designing intelligent systems that can adapt to the characteristics of their users. This paper focuses on the automatic analysis and classification of engagement based on ...humans' and robot's personality profiles in a triadic human-human-robot interaction setting. More explicitly, we present a study that involves two participants interacting with a humanoid robot, and investigate how participants' personalities can be used together with the robot's personality to predict the engagement state of each participant. The fully automatic system is first trained to predict the Big Five personality traits of each participant by extracting individual and interpersonal features from their nonverbal behavioural cues. Second, the output of the personality prediction system is used as an input to the engagement classification system. Third, we focus on the concept of "group engagement", which we define as the collective engagement of the participants with the robot, and analyze the impact of similar and dissimilar personalities on the engagement classification. Our experimental results show that: 1) using the automatically predicted personality labels for engagement classification yields an F-measure on par with using the manually annotated personality labels, demonstrating the effectiveness of the automatic personality prediction module proposed; 2) using the individual and interpersonal features without utilizing personality information is not sufficient for engagement classification, instead incorporating the participants and robots personalities with individual/interpersonal features increases engagement classification performance; and 3) the best classification performance is achieved when the participants and the robot are extroverted, while the worst results are obtained when all are introverted.
Face landmarking, defined as the detection and localization of certain characteristic points on the face, is an important intermediary step for many subsequent face processing operations that range ...from biometric recognition to the understanding of mental states. Despite its conceptual simplicity, this computer vision problem has proven extremely challenging due to inherent face variability as well as the multitude of confounding factors such as pose, expression, illumination and occlusions. The purpose of this survey is to give an overview of landmarking algorithms and their progress over the last decade, categorize them and show comparative performance statistics of the state of the art. We discuss the main trends and indicate current shortcomings with the expectation that this survey will provide further impetus for the much needed high-performance, real-life face landmarking operating at video rates.
Cognitive impairment features in neuropsychiatric conditions and when undiagnosed can have a severe impact on the affected individual's safety and ability to perform daily tasks. Virtual Reality (VR) ...systems are increasingly being explored for the recognition, diagnosis and treatment of cognitive impairment. In this paper, we describe novel VR-derived measures of cognitive performance and show their correspondence with clinically-validated cognitive performance measures. We use an immersive VR environment called VStore where participants complete a simulated supermarket shopping task. People with psychosis (k=26) and non-patient controls (k=128) participated in the study, spanning ages 20-79 years. The individuals were split into two cohorts, a homogeneous non-patient cohort (k=99 non-patient participants) and a heterogeneous cohort (k=26 patients, k=29 non-patient participants). Participants' spatio-temporal behaviour in VStore is used to extract four features, namely, route optimality score, proportional distance score, execution error score, and hesitation score using the Traveling Salesman Problem and explore-exploit decision mathematics. These extracted features are mapped to seven validated cognitive performance scores, via linear regression models. The most statistically important feature is found to be the hesitation score. When combined with the remaining extracted features, the multiple linear regression model resulted in statistically significant results with R2 = 0.369, F-Stat = 7.158, p(F-Stat) = 0.000128.
•A new evaluation procedure for action localization is proposed.•We introduce performance graphs showing quantity as a function of quality.•A single performance measure integrates out quality ...constraints.•Soft upper bounds estimated from experimental data.•The entry algorithms in the ICPR 2012 HARL competition are evaluated.
Evaluating the performance of computer vision algorithms is classically done by reporting classification error or accuracy, if the problem at hand is the classification of an object in an image, the recognition of an activity in a video or the categorization and labeling of the image or video. If in addition the detection of an item in an image or a video, and/or its localization are required, frequently used metrics are Recall and Precision, as well as ROC curves. These metrics give quantitative performance values which are easy to understand and to interpret even by non-experts. However, an inherent problem is the dependency of quantitative performance measures on the quality constraints that we need impose on the detection algorithm. In particular, an important quality parameter of these measures is the spatial or spatio-temporal overlap between a ground-truth item and a detected item, and this needs to be taken into account when interpreting the results.
We propose a new performance metric addressing and unifying the qualitative and quantitative aspects of the performance measures. The performance of a detection and recognition algorithm is illustrated intuitively by performance graphs which present quantitative performance values, like Recall, Precision and F-Score, depending on quality constraints of the detection. In order to compare the performance of different computer vision algorithms, a representative single performance measure is computed from the graphs, by integrating out all quality parameters. The evaluation method can be applied to different types of activity detection and recognition algorithms. The performance metric has been tested on several activity recognition algorithms participating in the ICPR 2012 HARL competition.
The various image-processing stages in a digital camera pipeline leave telltale footprints, which can be exploited as forensic signatures. These footprints consist of pixel defects, of unevenness of ...the responses in the charge-coupled device sensor, black current noise, and may originate from proprietary interpolation algorithms involved in color filter array. Various imaging device (camera, scanner, etc.) identification methods are based on the analysis of these artifacts. In this paper, we set to explore three sets of forensic features, namely binary similarity measures, image-quality measures, and higher order wavelet statistics in conjunction with SVM classifiers to identify the originating camera. We demonstrate that our camera model identification algorithm achieves more accurate identification, and that it can be made robust to a host of image manipulations. The algorithm has the potential to discriminate camera units within the same model.
Graphs and hyper-graphs are frequently used to recognize complex and often non-rigid patterns in computer vision, either through graph matching or point-set matching with graphs. Most formulations ...resort to the minimization of a difficult energy function containing geometric or structural terms, frequently coupled with data attached terms involving appearance information. Traditional methods solve the minimization problem approximately, for instance resorting to spectral techniques. In this paper, we deal with the spatio-temporal data, for a concrete example, human actions in video sequences. In this context, we first make three realistic assumptions: (i) causality of human movements; (ii) sequential nature of human movements; and (iii) one-to-one mapping of time instants. We show that, under these assumptions, the correspondence problem can be decomposed into a set of subproblems such that each subproblem can be solved recursively in terms of the others, and hence an efficient exact minimization algorithm can be derived using dynamic programming approach. Secondly, we propose a special graphical structure which is elongated in time. We argue that, instead of approximately solving the original problem, a solution can be obtained by exactly solving an approximated problem. An exact minimization algorithm is derived for this structure and successfully applied to action recognition in two settings: video data and Kinect coordinate data.
In this paper, we propose a novel multimodal framework for automatically predicting the impressions of extroversion, agreeableness, conscientiousness, neuroticism , openness, attractiveness and ...likeability continuously in time and across varying situational contexts. Differently from the existing works, we obtain visual-only and audio-only annotations continuously in time for the same set of subjects, for the first time in the literature, and compare them to their audio-visual annotations. We propose a time-continuous prediction approach that learns the temporal relationships rather than treating each time instant separately. Our experiments show that the best prediction results are obtained when regression models are learned from audio-visual annotations and visual cues, and from audio-visual annotations and visual cues combined with audio cues at the decision level. Continuously generated annotations have the potential to provide insight into better understanding which impressions can be formed and predicted more dynamically, varying with situational context, and which ones appear to be more static and stable over time.
Humanoid robot avatars are a potential new telecommunication tool, whereby a user is remotely represented by a robot that replicates their arm, head, and possible face movements. They have been shown ...to have a number of benefits over more traditional media such as phones or video calls. However, using a teleoperated humanoid as a communication medium inherently changes the appearance of the operator, and appearance-based stereotypes are used in interpersonal judgments (whether consciously or unconsciously). One such judgment that plays a key role in how people interact is personality. Hence, we have been motivated to investigate if and how using a robot avatar alters the perceived personality of teleoperators. To do so, we carried out two studies where participants performed 3 communication tasks, solo in study one and dyadic in study two, and were recorded on video both with and without robot mediation. Judges recruited using online crowdsourcing services then made personality judgments of the participants in the video clips. We observed that judges were able to make internally consistent trait judgments in both communication conditions. However, judge agreement was affected by robot mediation, although which traits were affected was highly task dependent. Our most important finding was that in dyadic tasks personality trait perception was shifted to incorporate cues relating to the robot’s appearance when it was used to communicate. Our findings have important implications for telepresence robot design and personality expression in autonomous robots.
Developing automatic personality predictors requires generating reliable annotations, i.e., ground truth. To date, researchers have relied on the overall ratings provided for a whole video sequence, ...either obtained by self-assessment or provided by external observers. In this paper, we propose a novel personality assessment approach, where we ask external observers to continuously provide ratings along multiple dimensions ranging from 0 to 100 along time, and we generate continuous annotations in space and time. In addition to the widely used Big Five personality dimensions, we introduce three more dimensions that have the potential to gauge the reliability of the perceived social and trait judgements in the context of varying situational interactions between a human subject and virtual characters. Our results demonstrate the viability of the proposed approach and the plausible relationship between the extracted features and perceived trait and social dimensions. Annotations obtained continuously in time and in trait-social dimensional space showed that a number of dimensions appear to be more static and stable over time while other dimensions appear to be more dynamic.