Mark G. Frank

ORCID: 0000-0002-0906-1497
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Deception detection and forensic psychology
  • Psychopathy, Forensic Psychiatry, Sexual Offending
  • Emotion and Mood Recognition
  • Face Recognition and Perception
  • Psychology of Moral and Emotional Judgment
  • Misinformation and Its Impacts
  • Emotions and Moral Behavior
  • Social and Intergroup Psychology
  • Adversarial Robustness in Machine Learning
  • Face and Expression Recognition
  • Memory Processes and Influences
  • Communication in Education and Healthcare
  • Authorship Attribution and Profiling
  • Anomaly Detection Techniques and Applications
  • Evolutionary Psychology and Human Behavior
  • Stalking, Cyberstalking, and Harassment
  • Hate Speech and Cyberbullying Detection
  • Digital Communication and Language
  • Psychology of Social Influence
  • Multisensory perception and integration
  • Advanced Malware Detection Techniques
  • Interpreting and Communication in Healthcare
  • Face recognition and analysis
  • Information and Cyber Security
  • Humor Studies and Applications

University at Buffalo, State University of New York
2014-2023

University of California, Los Angeles
2023

Rutgers, The State University of New Jersey
1997-2006

University of California, San Diego
2006

Buffalo State University
2006

Rütgers (Germany)
1999

Rutgers Sexual and Reproductive Health and Rights
1999

Cornell University
1988

University of Colorado Denver
1982

We present a systematic comparison of machine learning methods applied to the problem fully automatic recognition facial expressions. report results on series experiments comparing engines, including AdaBoost, support vector machines, linear discriminant analysis. also explored feature selection techniques, use AdaBoost for prior classification by SVM or LDA. Best were obtained selecting subset Gabor filters using followed with machines. The system operates in real-time, and 93% correct...

10.1109/cvpr.2005.297 article EN 2005-07-27

We present the Computer Expression Recognition Toolbox (CERT), a software tool for fully automatic real-time facial expression recognition, and officially release it free academic use. CERT can automatically code intensity of 19 different actions from Facial Action Unit Coding System (FACS) 6 prototypical expressions. It also estimates locations 10 features as well 3-D orientation (yaw, pitch, roll) head. On database posed expressions, Extended Cohn-Kanade (CK+[1]), achieves an average...

10.1109/fg.2011.5771414 article EN 2011-03-01

Spontaneous facial expressions differ from posed in both which muscles are moved, and the dynamics of movement. Advances field automatic expression measurement will require development assessment on spontaneous behavior. Here we present preliminary results a task action detection expressions. We employ user independent fully system for real time recognition actions Facial Action Coding System (FACS). The automatically detects frontal faces video stream coded each frame with respect to 20...

10.4304/jmm.1.6.22-35 article EN Journal of Multimedia 2006-09-01

Black is viewed as the color of evil and death in virtually all cultures.With this association mind, we were interested whether a cue subtle person's clothing might have significant impact on his or her behavior.To test possibility, examined professional football ice hockey teams that wear black uniforms are more aggressive than those nonblack uniforms.An analysis penalty records National Football League Hockey indicate with both sports ranked near top their leagues penalties throughout...

10.1037/0022-3514.54.1.74 article EN Journal of Personality and Social Psychology 1988-01-01

In highly social species such as humans, faces have evolved to convey rich information for interaction, including expressions of emotions and pain [1Darwin C. The Expression the Emotions in Man Animals. Murray, London1872Crossref Google Scholar, 2Ekman P. argument evidence about universals facial emotion.in: Raskin D.C. Psychological Methods Criminal Investigation Evidence. Springer Publishing Company, New York1989: 297-332Google 3Frank M.G. Ekman Friesen W.V. Behavioral markers...

10.1016/j.cub.2014.02.009 article EN publisher-specific-oa Current Biology 2014-03-01

Research suggests that most people cannot tell from demeanor when others are lying. Such poor performance is typical not only of laypeople but also professionals concerned with In this study, three professional groups special interest or skill in deception, two law-enforcement and a select group clinical psychologists, obtained high accuracy judging videotapes who were lying telling the truth about their opinions. These findings strengthen earlier evidence some lie catchers highly accurate,...

10.1111/1467-9280.00147 article EN Psychological Science 1999-05-01

The authors investigated whether accuracy in identifying deception from demeanor high-stake lies is specific to those or generalizes other lies. In Experiment 1, 48 observers judged 2 different groups of men were telling about a mock theft (crime scenario) their opinion (opinion scenario). found that observers' judging the crime scenario was positively correlated with scenario. replicated results as well P. Ekman and M. O'Sullivan's (1991) finding positive correlation between ability detect...

10.1037//0022-3514.72.6.1429 article EN Journal of Personality and Social Psychology 1997-01-01

We present results on a user independent fully automatic system for real time recognition of facial actions from the action coding (FACS). The automatically detects frontal faces in video stream and codes each frame with respect to 20 units. preliminary task detection spontaneous expressions during discourse. Support vector machines AdaBoost classifiers are compared. For both classifiers, output margin predicts unit intensity

10.1109/fgr.2006.55 article EN 2006-04-28

10.1037/0022-3514.72.6.1429 article EN Journal of Personality and Social Psychology 1997-01-01

Abstract Can we train people to detect deception? It is the contention of this article that communication scholars should learn how law enforcement professionals on high stake lies, like those faced by police, judges, customs officials, immigration and so forth. proposed in order know whether can or bother deception, each training study must meet 6 challenges: (1) relevance, (2) stakes, (3) proper training, (4) testing, (5) generalizability across situations, (6) over time. Our quantitative...

10.1080/00909880305377 article EN Journal of Applied Communication Research 2003-01-01

10.1515/humr.1993.6.1.9 article EN Humor - International Journal of Humor Research 1993-01-01

The view that certain facial expressions of emotion are universally agreed on has been challenged by studies showing the forced-choice paradigm may have artificially forced agreement. This article addressed this methodological criticism offering participants opportunity to select a none these terms correct option from list labels in modified paradigm. results show agreement label for particular is still greater than chance, artifactual incorrect obviated, when asked judge novel expression,...

10.1037/0022-3514.80.1.75 article EN Journal of Personality and Social Psychology 2001-01-01

The psychological literature suggests that establishing rapport between interviewer and subject — whether in clinical, experimental or forensic settings is likely to enhance the quality of interaction. Yet there are surprisingly few studies test this assumption. This article reports a study effect on eyewitness recall dramatic videotaped event by creating three interviewer-attitude conditions "rapport", "neutral" "abrupt". Participants were randomly assigned conditions, was elicited two...

10.1375/pplt.2002.9.1.69 article EN Psychiatry Psychology and Law 2002-06-01

Emotions can drive intergroup behavior, including violence. We propose that anger, contempt, and disgust (ANCODI) work together in combination to motivate action, devaluation of the other group, then elimination their members. tested ANCODI hypothesis by examining speeches given leaders extreme political groups prior major events or rallies either turned violent (e.g., Kristallnacht Nazi Germany) did not Gandhi’s Salt March India). Three studies assessed these year critical event coded for...

10.1177/0963721415595023 article EN Current Directions in Psychological Science 2015-10-01

The authors investigated whether the ability to appear truthful is specific deception situations. Male participants were interrogated after they took part in 2 high-stake situations, one involving a mock crime and another false opinion. videotaped interrogations from each situation shown independent groups of undergraduate observers. proportion observers who judged participant as correlated highly with same other situation. This was not physiognomy judgments. Follow-up studies revealed that...

10.1037/0022-3514.86.3.486 article EN Journal of Personality and Social Psychology 2004-01-01

10.1007/s10919-010-0102-1 article EN Journal of Nonverbal Behavior 2011-02-01

Anger, contempt, and disgust are emotions associated with violations of ethics morality, recent theoretical work has suggested that they important drivers group-based aggression violence. We test this hypothesis by examining the expressed leaders ideologically motivated groups when speaking about outgroups oppose. analyzed content their speeches at three points in time before an identified act or resistance. provide initial evidence leaders' expressions anger, increase immediately acts...

10.1080/19434472.2012.716449 article EN Behavioral Sciences of Terrorism and Political Aggression 2012-08-28
Coming Soon ...