Naive Observers Research Articles

What Makes a Movement Human‐Like?

AbstractWith the advancement of AI‐generated human motion, it is of increasing importance to think about how we distinguish real human motion from machine‐generated movements. In this study, we recruited professional performers to use the whole body to make a short movement to inform potential observers that they are real humans (instead of machines). Their movements were captured with a motion capture system (Vicon) and later reduced to dynamic point‐like displays (biological motion). They were interviewed after the recording to provide their acting strategies. Naive observers who did not participate in the motion data collection were recruited to watch these videos and judge whether the biological motions looked human‐like or not (YES/NO), as well as to report their judging criteria. The major factors extracted from these reports include kinematics, context, body mechanics, and principles of physical laws. We discuss the impact of these criteria and how they may possibly help improve the future generation of human‐like motions.

Age Reduction After Face-Lift Surgery in Chinese Population: An Outcome Study Using Artificial Intelligence and Objective Observer-Based Assessment.

The literature is replete with favorable face-lift results, yet the objective facial rejuvenation outcome measures in Chinese women have remained poorly understood. The purpose of the study is to objectively evaluate the apparent age (AA) reduction in Chinese women following face-lift by artificial intelligence (AI) and objective observers. Standardized pre- and postoperative (1-year) images of 48 patients undergoing face-lift procedures were analyzed by AI to estimate AA. Additionally, 10 blinded, naive observers viewed each patient's images and assessed AA. The accuracy of AA and reduction in AA were evaluated and compared between the two methods. FACE-Q surveys were employed to measure patient-reported facial esthetic outcomes. The AI demonstrated higher precision than the observers in age estimation, with a mean absolute error of 3.34 years and 90% Pearson correlation. AA reduction generated by AI was significantly lower than that by observers, with a mean reduction of 3.75 ± 3.93 and 4.51 ± 1.20, respectively (p < 0.05). However, both methods showed less AA reduction than patient self-appraisal (-7.3 years). Improvements in facial rejuvenation following face-lift surgery is relevant to the patient's preoperative aging status. Patients whose pre-AA was greater than chronological age (CA) became "back to normal," while those whose pre-AA was less than CA became "turning back the clock." The utilization of AI could provide objective, evidence-based data in the field of face-lift surgery. As a simple, complete, and time-sparing method, AI is expected to be routinely used in clinical trials and practice. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Оценка индивидуально-психологических характеристик и уровня доверия по фотоизображению лица незнакомого человека до и после непосредственного перцептивного взаимодействия

&lt;p&gt;The article presents the results of a study of the influence of direct perceptual interaction on the assessment of the individual psychological characteristics of a stranger and the level of trust/distrust in him. The problem of the influence of direct perceptual interaction in conditions of interpersonal perception still remains relevant and requires thorough experimental study. The main assumption of the work is that ideas about a stranger, including a complex dialectical interaction of trust/distrust, will differ significantly before and after direct perceptual interaction. The assessment of individual psychological characteristics was carried out using the &amp;ldquo;Personal Differential&amp;rdquo; technique, trust/distrust using the &amp;ldquo;Perceptive Trust Assessment Test&amp;rdquo;. The results show that the experience of brief nonverbal face-to-face interaction reduces the number of significant differences in the ratings of naive observers with the ratings of experts. Regardless of the facial morphotype, after the experience of interaction, all sitters are perceived by observers with a bias towards socially desirable individual psychological characteristics, with the exception of the only characteristic (stubborn) in the assessments of the round morphotype. The experience of non-verbal face-to-face interaction has a significant impact on the formation of a more trusting attitude towards a stranger in an outside observer, in contrast to the level of trust formed from a photograph.&lt;/p&gt;

EasyEyes - A new method for accurate fixation in online vision testing.

Online methods allow testing of larger, more diverse populations, with much less effort than in-lab testing. However, many psychophysical measurements, including visual crowding, require accurate eye fixation, which is classically achieved by testing only experienced observers who have learned to fixate reliably, or by using a gaze tracker to restrict testing to moments when fixation is accurate. Alas, both approaches are impractical online as online observers tend to be inexperienced, and online gaze tracking, using the built-in webcam, has a low precision (±4 deg). EasyEyes open-source software reliably measures peripheral thresholds online with accurate fixation achieved in a novel way, without gaze tracking. It tells observers to use the cursor to track a moving crosshair. At a random time during successful tracking, a brief target is presented in the periphery. The observer responds by identifying the target. To evaluate EasyEyes fixation accuracy and thresholds, we tested 12 naive observers in three ways in a counterbalanced order: first, in the laboratory, using gaze-contingent stimulus presentation; second, in the laboratory, using EasyEyes while independently monitoring gaze using EyeLink 1000; third, online at home, using EasyEyes. We find that crowding thresholds are consistent and individual differences are conserved. The small root mean square (RMS) fixation error (0.6 deg) during target presentation eliminates the need for gaze tracking. Thus, this method enables fixation-dependent measurements online, for easy testing of larger and more diverse populations.

Contribution of Affect and Cognition in Shaping Aesthetic Responses

The human experience of art is unique, being associated with exceptional and transcendent states of consciousness. These experiences are formed based on the interaction between the work of art itself, the observer, and the context. Using the multilevel modelling with crossed random effects analysis, we explored the connection between the affective and cognitive appraisals of a visual work of art and the aesthetic judgment. Two experiments were performed. In the first, lay persons appraised figural paintings with pleasant and unpleasant content. In the second experiment, abstract and realistic paintings were appraised. The results indicate a strong connection between affective appraisal and the aesthetic judgment, especially with the assessment of beauty. Cognitive appraisals are less closely connected to aesthetic appraisals. These results suggest that naive observers use everyday, practical perception when evaluating works of art, and that paintings which evoke "sweet", pleasant, hedonic emotions will be assessed as more aesthetically pleasing. The deviation of a painting from traditional art canons further strengthens the reliance on everyday perception in lay persons. The implications of these results are discussed.

When will AI misclassify? Intuiting failures on natural images.

Machine recognition systems now rival humans in their ability to classify natural images. However, their success is accompanied by a striking failure: a tendency to commit bizarre misclassifications on inputs specifically selected to fool them. What do ordinary people know about the nature and prevalence of such classification errors? Here, five experiments exploit the recent discovery of "natural adversarial examples" to ask whether naive observers can predict when and how machines will misclassify natural images. Whereas classical adversarial examples are inputs that have been minimally perturbed to induce misclassifications, natural adversarial examples are simply unmodified natural photographs that consistently fool a wide variety of machine recognition systems. For example, a bird casting a shadow might be misclassified as a sundial, or a beach umbrella made of straw might be misclassified as a broom. In Experiment 1, subjects accurately predicted which natural images machines would misclassify and which they would not. Experiments2 through 4 extended this ability to how the images would be misclassified, showing that anticipating machine misclassifications goes beyond merely identifying an image as nonprototypical. Finally, Experiment 5 replicated these findings under more ecologically valid conditions, demonstrating that subjects can anticipate misclassifications not only under two-alternative forced-choice conditions (as in Experiments 1-4), but also when the images appear one at a time in a continuous stream-a skill that may be of value to human-machine teams. We suggest that ordinary people can intuit how easy or hard a natural image is to classify, and we discuss the implications of these results for practical and theoretical issues at the interface of biological and artificial vision.

Perceptions of Movement Patterns and Concealment Detection in Naive Observers and Law Enforcement Officers: A Lens Model Analysis

This research investigates whether police officers can reliably use behavioral cues to determine whether a person is concealing an object. Using a Lens Model framework, we performed a mega-analysis of three experiments. In each study, officers and laypersons judged whether people were concealing an object and reported “articulable behaviors” they used to perform this task. Although participants were able to articulate behaviors that they believed were helpful, results showed that these behaviors were not related to whether the person was actually concealing. Officers and laypersons were equally poor at judging whether someone was concealing or not. Current officer training on the use of nonverbal behaviors to determine who is concealing a dangerous object may be ineffective, and a reconsideration of training is warranted. In light of the findings, requiring officers to provide “articulable behaviors” in Fourth Amendment cases may not provide a sufficient safeguard against unreasonable searches of civilians.

Looking tight: Visual judgments of knot strength reveal the limits of physical scene understanding

While early studies cataloged striking errors of physical scene understanding in naive observers, a resurgence of research has instead revealed a remarkable ability to intuit how physical scenes will unfold. Properties such as stability, mass, gravity and kinematics may all elicit accurate intuitions, especially when presented in naturalistic settings. A leading interpretation of these findings is that physical scene understanding recruits a general-purpose “physics engine”. Under this theory, the mind simulates how a scene will unfold by modeling or approximating its physics, and only fails for physics problems that are contrived or presented without context. But might there be tasks that persistently strain physical reasoning, even when presented naturalistically and in realistic contexts? Here, 5 experiments explore this question by evaluating intuitions about the strength of simple knots. Knots are naturalistic stimuli that are ubiquitous across cultures and time periods, and in many contexts evaluating them correctly can spell the difference between safety and peril. Despite this, here we show that naive observers fail to discern even striking differences in strength between knots. In a series of two-alternative forced-choice tasks, observers viewed simple “bends” (i.e., knots joining two lengths of string) and decided which would require more force to undo. Though the relative strength of these bends is well-documented, observers’ judgments completely failed to reflect these distinctions—including in naturalistic photographs (E1), idealized renderings (E2), dynamic videos (E3), and even when accompanied by schematic diagrams of the knots’ structures (E4). Moreover, these failures persisted despite observers demonstrating visual understanding of the topological differences between the knots (E5); in other words, even when observers knew exactly what kind of knot they were viewing, they failed to extract or predict its physical behavior. These results expose a blindspot in physical reasoning, posing a new kind of challenge to general-purpose theories of scene understanding.

A comparable truth baseline improves truth/lie discrimination

AbstractIn a comparable truth baseline (CTB), a knowingly truthful baseline statement is compared to a statement of interest, and deviations in verbal details possibly indicate deceit. In two experiments, we investigated whether a CTB can improve truth/lie discrimination when verbal details are coded by independent raters (Experiment 1) and when judged by naive observers (Experiment 2). In addition, we investigated whether lie tellers would calibrate their lies to match the detailedness of their baseline. Results showed no evidence of calibration. As expected, truths were more detailed than their corresponding baselines, while lies were less detailed. Significant differences emerged for spatial, visual and action details. Experiment 2 did not show that a CTB improved observers' lie detection accuracy. Taken together, our results showed that a deviation in details from a CTB may serve as a helpful aid in lie detection.

Interpersonal Consequences of Deceptive Expressions of Sadness.

Emotional expressions evoke predictable responses from observers; displays of sadness are commonly met with sympathy and help from others. Accordingly, people may be motivated to feign emotions to elicit a desired response. In the absence of suspicion, we predicted that emotional and behavioral responses to genuine (vs. deceptive) expressers would be guided by empirically valid cues of sadness authenticity. Consistent with this hypothesis, untrained observers (total N = 1,300) reported less sympathy and offered less help to deceptive (vs. genuine) expressers of sadness. This effect was replicated using both posed, low-stakes, laboratory-created stimuli, and spontaneous, real, high-stakes emotional appeals to the public. Furthermore, lens models suggest that sympathy reactions were guided by difficult-to-fake facial actions associated with sadness. Results suggest that naive observers use empirically valid cues to deception to coordinate social interactions, providing novel evidence that people are sensitive to subtle cues to deception.

Use of Target Species in Citizen Science Fungi Recording Schemes

Use of Target Species in Citizen Science Fungi Recording Schemes

Test-retest Reliability of the qReading Method in Normally Sighted Young Adults.

We recently developed a novel Bayesian adaptive method, qReading, to measure reading function. The qReading method has both the efficiency and excellent test-retest reliability in normally sighted young adults to make it an excellent candidate for future studies of its value in diagnosis and longitudinal evaluation of treatment and/or rehabilitation outcomes. A novel Bayesian adaptive method, qReading, was recently developed to measure reading function. Here we performed a systematic assessment of the test-retest reliability of the qReading method. The variability of five repeated measurements of the reading curve was examined in two settings: within session and between sessions. For the within-session design, we considered two subpopulations: naive observers and experienced observers. All observers were normally sighted young adults. For each set of data, in addition to examining the intrinsic precision of the qReading method (the half width of the credible interval of the posterior distribution of the estimated performance), we computed four metrics to assess repeatability: standard deviation, Bland-Altman coefficient of repeatability, correlation coefficient, and Fractional Rank Precision. Extrinsic factors such as observer, time interval between repeated measures, and observer experience all contribute to the variation across measurements. Nevertheless, the four metrics consistently show that the variability across five repeated measurements is small for each set of data. This is true even without taking learning effects into account (standard deviations, ≤0.092 log10 units; Bland-Altman coefficient of repeatability, ≤0.15 (log10)2 units; correlation coefficient, ≥0.91; and Fractional Rank Precision, ≥0.81). The qReading method has excellent test-retest reliability in normally sighted young adults.

The effects of recent perceptual history on stream-bounce perception.

We examine perceptual disambiguation and crossmodal interactions by considering the effect of recent perceptual history on stream-bounce perception. First, we tested the assumption that the audio-visual stream-bounce effect (visual-only trials mostly stream, whereas audio-visual trials mostly bounce) reflects some intrinsic preference for streaming that is broken by sound. Instead, we found that for naïve observers, visual-only stimuli are bistable and bias free. In intermixed trials, sound acts as a polarizing factor (rather than a bounce-inducing factor) and has as much effect on visual-only trials as it does on audio-visual trials. Second, temporal context exerts a comparative influence and exposure to audio-visual stimuli influences responses to visual-only stimuli and vice-versa. Finally, there is a serial dependence in responses and the current stimulus (unisensory or multisensory) is interpreted with a bias to recent interpretations. Recent perceptual history exerts a substantial influence on the perception of stream-bounce stimuli. This influence occurs in the unisensory case and is in line with an extensive literature on visual bistability; it extends to the multisensory case, and there are interactions between the 2 cases. Our combined findings support a role for top-down interpretational influences in the stream-bounce effect and stream-bounce perception more generally. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Intrapersonal Behavioral Coordination and Expressive Accuracy During First Impressions

What factors influence how accurately we express our personalities? Here, we investigated the role of targets’ nonverbal expressivity or the intrapersonal coordination between head and body movements. To do so, using a novel movement quantification method, we examined whether variability in a person’s behavioral coordination was related to how accurately their personality was perceived by naive observers. Targets who exhibited greater variability in intrapersonal behavior coordination, indicating more expressive behavior, were perceived more accurately on high observability personality items, such as how energetic and helpful they are. Moreover, these associations held controlling for other indicators of overall movement, self- and perceiver-rated extroversion, as well as how engaging and likable targets were perceived to be. This provides preliminary evidence that variability in intrapersonal behavioral coordination may be a unique behavioral indicator of expressive accuracy, although further research that replicates these findings and examines the causal associations is needed.

The Face of Social Networks: Naive Observers’ Accurate Assessment of Others’ Social Network Positions From Faces

We examined whether, even at zero acquaintance, observers accurately infer others’ social network positions—specifically, the number and patterning of social ties (e.g., brokerage—the extent to which a person bridges disconnected people) and the trait impressions that support this accuracy. We paired social network data (n = 272 professional school students), with naive observers’ (n = 301 undergraduates) judgments of facial images of each person within the network. Results revealed that observers’ judgments of targets’ number of friends were predicted by the actual number of people who considered the target a friend (in-degree centrality) and that perceived brokerage was significantly predicted by targets’ actual brokerage. Lens models revealed that targets’ perceived attractiveness, dominance, warmth, competence, and trustworthiness supported this accuracy, with attractiveness and warmth most associated with perceptions of popularity and brokerage. Overall, we demonstrate accuracy in naive observers’ judgments of social network position and the trait impressions supporting these inferences.

Interaction between image and text during the process of biblical art reception.

In our exploratory study, we ask how naive observers, without a distinct religious background, approach biblical art that combines image and text. For this purpose, we choose the book ‘New biblical figures of the Old and New Testament’ published in 1569 as source of the stimuli. This book belongs to the genre of illustrated Bibles, which were very popular during the Reformation. Since there is no empirical knowledge regarding the interaction between image and text during the process of such biblical art reception, we selected four relevant images from the book and measured the eye movements of participants in order to characterize and quantify their scanning behavior related to such stimuli in terms of i) looking at text (text usage), ii) text vs. image interaction measures (semantic or contextual relevance of text), and iii) narration. We show that texts capture attention early in the process of inspection and that text and image interact. Moreover, semantics of texts are used to guide eye movements later through the image, supporting the formation of the narrative.

Rapid measurement of the adult worker population size in honey bees

Changes in agricultural practices have lead to pollination deficits in entomophilous crops, leading to a growing interest in supplementing farmlands with managed colonies of honey bee, Apis mellifera. However, the metrics of a colony as a pollination unit is controversial due to the wide range of adult population sizes encountered in a colony, especially in relation with the time of year and beekeeping management. Correctly measuring the number of adult honey bees per hive is critical for farmers to adjust the number of colonies they need to meet crop pollination demand. We tested a simple non-invasive method to estimate the adult worker population size of colonies based on common beekeeping handlings. This method consisted in counting the number of inter-frames covered with adult bees (called IFB thereafter) from above the hive body. Based on the monitoring of 181 colonies, we investigated the nature of the relation between IFB and the adult bee population size and its context-dependence to the meterological conditions and hive type. We then evaluated the possible improvement of the method with additional IFB counted in the supers and from below the hive body. Finally, we analysed the robustness of the method by comparing estimates obtained from colonies observed by experimented and naive observers. We revealed a clear-cut logarithmic relation between the IFB and the adult population size, covering the effects of meteorological conditions and hive type. The counting of IFB from above the hive body were particularly sensitive to meteorological conditions, unlike those counted from below the hive body. Moreover, the counting of additional IFB from the supers slightly improved the estimates of adult population size. Interestingly, no difference of estimate was detected between experimented and naive observers, suggesting applied simplicity of the method. The IFB counting method thus provides a simple, non-invasive and robust indicator of the adult population size of a managed honey bee colony. The counting of IFB from below the hive body should be recommend due to the sensitivity to meteorological conditions of the counting of IFB from above the hive body. Beyond crop pollination, we also highlighted application perspectives of this method as an indicator of survival probability. This method can therefore be viewed as a standard for routine field monitoring (i) to help farmers to estimate rigorously the number of colonies they need to meet the crop pollination demand and (ii) to help beekeepers assessing the mortality risk of their colonies.

Confocal Laser Endomicroscopy Interpretation and Differentiation of Pancreatic Cysts: A Randomized Trial of Teaching Modalities

ABSTRACT Background EUS-guided needle-based confocal laser endomicroscopy (nCLE) has not been widely adopted for the differentiation of pancreatic cystic lesions (PCLs), perhaps due to a perceived difficulty in learning novel CLE image patterns. Hence, we sought to investigate the optimal teaching modality for interpretation of nCLE imaging from PCLs. Methods Sixteen nCLE-naive observers blinded to clinical data were randomized into didactic (classroom-based) versus self-directed (computer-based) teaching groups to review nCLE videos and differentiate mucinous and non-mucinous PCLs. The study was conducted concurrently for both groups in 3 phases. Phase-1-Teaching: both groups received an overview of EUS-nCLE of PCLs. Phase-2-Training: assessment of 20 EUS-nCLE subject-videos; the didactic group had a feedback session with an nCLE expert while the self-directed group received this information via pre-recorded presentation. Phase-3-Testing: assessment of 50 EUS-nCLE subject-videos. Results For all observers (n = 16), the diagnostic accuracy for nCLE-based differentiation of mucinous from non-mucinous PCLs was higher (p=0.005) in the Phase-3-Testing (94.6%, 95%CI: 92-96%) than in Phase-2-Training (89.9%, 95%CI: 85-93%). During Phase-3-Testing, both the didactic and self-directed teaching groups achieved a comparable (p=0.48) diagnostic accuracy of 93.9% and 95.4%, respectively. The interobserver agreement (kappa, standard error) for the differentiation of mucinous from non-mucinous PCLs improved from Phase-2-Training to Phase-3-Testing stage, and was “substantial” for both the didactic (k=0.81, 0.03) and self-directed (k=0.79, 0.03) training groups. Conclusion Notwithstanding didactic and self-directed teaching, a ‘training’ and ‘test’ strategy accomplished high diagnostic accuracies and considerable interobserver agreement among naive observers for EUS-nCLE image differentiation of PCLs; Clinical trial NCT02516488 ( https://clinicaltrials.gov/ct2/show/NCT02516488 )

Broadening the stimulus set: Introducing the American Multiracial Faces Database.

Face-based perceptions form the basis for how people behave towards each other and, hence, are central to understanding human interaction. Studying face perception requires a large and diverse set of stimuli in order to make ecologically valid, generalizable conclusions. To date, there are no publicly available databases with a substantial number of Multiracial or racially ambiguous faces. Our systematic review of the literature on Multiracial person perception documented that published studies have relied on computer-generated faces (84% of stimuli), Black-White faces (74%), and male faces (63%). We sought to address these issues, and to broaden the diversity of available face stimuli, by creating the American Multiracial Faces Database (AMFD). The AMFD is a novel collection of 110 faces with mixed-race heritage and accompanying ratings of those faces by naive observers that are freely available to academic researchers. The faces (smiling and neutral expression poses) were rated on attractiveness, emotional expression, racial ambiguity, masculinity, racial group membership(s), gender group membership(s), warmth, competence, dominance, and trustworthiness. The large majority of the AMFD faces are racially ambiguous and can pass into at least two different racial categories. These faces will be useful to researchers seeking to study Multiracial person perception as well as those looking for racially ambiguous faces in order to study categorization processes in general. Consequently, the AMFD will be useful to a broad group of researchers who are studying face perception.

Methods for determining equiluminance in terms of L/M cone ratios.

Heterochromatic flicker photometry (HFP), minimum motion (MM), and minimally distinct border (MDB) settings have often been used to determine equiluminance, a relative intensity setting for two chromaticities that, in theory, eliminates the responses of a luminance or achromatic psychophysical mechanism. These settings have been taken to reflect the relative contribution of the long (L) and medium (M) wavelength cones to luminance, which varies widely across individuals. The present study compares HFP, MM, and MDB using stimuli that do not modulate the short (S) wavelength cones, in both practiced and naïve observers. MDB was performed with both flashed and steadily viewed stimuli. Results are represented in the (∆L/L, ∆M/M) plane of cone contrast space. Considering both practiced and naïve observers, both MM and HFP had excellent within-subject precision and high test–retest reliability, whereas HFP also had low between-subject variability. The MDB tasks were less reliable and less precise. The mean L:M contrast ratios at equiluminance were lower for the two temporal tasks (HFP and MM) compared to the spatial tasks (MDB), perhaps consistent with the existence of multiple luminance mechanisms. Overall, the results suggest that the best method for determining equiluminance is HFP, with MM being a close second.