Cigdem Beyan

Post Doc
Postdoctoral Researcher

Contacts

Via Morego 30
+39 010 71781279

About

Cigdem Beyan is a postdoctoral researcher at Istituto Italiano di Tecnologia (IIT), Pattern Analysis and Computer Vision (PAVIS) department since September 2015. In PAVIS-IIT, she has been working on topics related to social signal processing i.e. emergent leader detection in small group interactions and deception detection in the wild which were realized using different machine learning techniques and audio-based, video-based and audio-visual nonverbal features.

She obtained her Ph.D. (2015) in School of Informatics (specializing Computer Vision and Pattern Recognition), University of Edinburgh, UK, under supervision of Prof. Robert B. Fisher. Her thesis was a part of EU project (FP7) called Fish4Knowledge, which includes fish behaviour understanding, trajectory analysis, anomaly detection, classification of imbalanced data, active learning and big data analysis.

Prior to that, she completed a MSc. (2010) in School of Informatics (specializing Computer Vision), Middle East Technical University, Turkey where she worked on multiple object tracking and abandoned object detection using thermal and visible band video data fusion.

Beyond her research background, she has a teaching experience (in Turkey and in UK) for 6 years as teaching assistant, guest lecturer, tutor, demonstrator and marker. Additionally, she became an Associate Fellow of the Higher Education Academy in recognition of attainment against the UK Professional Standards Framework for teaching and learning support in higher education in 2014

Interests

Social signal processing behaviour understanding trajectory analysis anomaly detection classification of imbalanced data

Projects

After September 2015

1) Social Scene Understanding: Multi-Person Action Localization and Group Behavior Analysis

2) Multi-modal Identification of Leaders in Small Group Social Interactions

For more info: https://www.iit.it/pavis/datasets/leadershipCorpus

3) Deception Detection using Multi-modal (Deep/ Hand-crafted Nonverbal) Features

For more info: http://pavis.iit.it/projects/deception-detection

 

 

Selected Publications

IIT AFFILIATED ONLY:

Book Chapters

C. Beyan, “Unusual Trajectory Detection: Advances”, Encyclopedia of Image Processing, 1st Edition, Phillip A. Laplante (Editor), Taylor & Francis Group: New York. In Press.

C. Beyan, “Fish Behavior Analysis”, In Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data, Chen-Burger et al. (Editors), Springer, doi: 10.1007/978-3-319-30208-9.

 

Journal Papers

C. Beyan, V. M. Katsageorgiou, R. Fisher, (2017), “Extracting Statistically Significant Behaviour from Fish Tracking Data With and Without Large Dataset Cleaning”, IET Computer Vision, doi: 10.1049/iet-cvi.2016.0462.

C. Beyan, F. Capozzi, C. Becchio, and V. Murino, (2017),“Prediction of the Leadership Style of an Emergent Leader Using Audio and Visual Nonverbal Features”, IEEE Transactions on Multimedia, doi: 10.1109/TMM.2017.2740062

 

International Conference/Workshop Papers

C. Beyan, F. Capozzi, C. Becchio, and V. Murino, (2017), “Multi-task Learning of Social Psychology Assessments and Nonverbal Features for Automatic Leadership Identification”, International Conference on Multimodal Interaction (ICMI), doi: 10.1145/3136755.3136812.

C. Beyan, V. M. Katsageorgiou, and V. Murino, (2017), “Moving as a Leader: Detecting Emergent Leadership in Small Groups using Body Pose”, ACM Multimedia, doi: 10.1145/3123266.3123404.

C.Beyan, F. Capozzi, C. Becchio, and V. Murino, (2016), “Identification of Emergent Leaders in a Meeting Scenario Using Multiple Kernel Learning”, International Workshop on Advancements in Social Signal Processing for Multimodal Interaction (ASSP4MI) in conjunction with International Conference on Multimodal Interaction (ICMI), Tokyo, Japan, doi: 10.1145/3005467.3005469.

C. Beyan, N. Carissimi, F. Capozzi, S. Vascon, M. Bustreo, A. Pierro, C. Becchio, and V. Murino, (2016) “Detecting emergent leader in a meeting environment using nonverbal visual features only”, International Conference on Multimodal Interaction (ICMI), Tokyo, Japan, doi: 10.1145/2993148.2993175.

 

MORE:

https://scholar.google.com/citations?user=VmjUxckAAAAJ&hl=en

SCOPUS Author ID: 43260919000

ORCID Author ID: 0000-0002-9583-0087

ResearcherID: Q-5101-2017

iit Publications

2018 Unusual Trajectory Detection: Advances
2017 Extracting Statistically Significant Behaviour from Fish Tracking Data With and Without Large Dataset Cleaning
2017 Moving as a Leader: Detecting Emergent Leadership in Small Groups using Body Pose
2017 Multi-task Learning of Social Psychology Assessments and Nonverbal Features for Automatic Leadership Identification
2017 Prediction of the Leadership Style of an Emergent Leader Using Audio and Visual Nonverbal Features
2016 Detecting emergent leader in a meeting environment using nonverbal visual features only
2016 Fish behavior analysis
2016 Identification of emergent leaders in a meeting scenario using multiple kernel learning