Sadjad
Asghari-Esfeden
LATEST PROJECTS
Project |0
Continuous Emotion Detection Using
EEG Signals and Facial Expressions
ICME 2014
We detect emotions from EEG signals and facial expressions in response to videos. Using power spectral features from EEG signals and faciallandmarks, we detect valence (pleasantness) levels for each frame continuously. We also study the effect of the changes in the stimulus (audio and visual features) on the emotional response of viewers. [pdf]
Project |01
Biologically Inspired Universal Dictionary of Visual Features for Object Recognition (Thesis
Project) - Computational Vision Lab, SCS, IPM, Tehran, Iran, June 2012 – Oct. 2012.
​
​We attempt to find a dictionary of visual features and use it in several tasks of object recondition and categorization. This universal dictionary is based on recent biological evidence of human visual system. Generally, we plan to produce a dictionary of images patches which finally are able to represent the input stimulus in higher processing levels.
​
Resources:
[1] T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, "Robust object recognition with cortex-like mechanisms," IEEE Trans Pattern Anal Mach Intell, vol. 29, pp. 411-26, Mar 2007.
[2] M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in cortex," Nat Neurosci,
vol. 2, pp. 1019-25, Nov 1999.
[3] K. Rajaei, S.-M. Khaligh-Razavi, M. Ghodrati, R. Ebrahimpour, and M. E. Shiri Ahmad Abadi, "A Stable Biologically Motivated Learning Mechanism for Visual Feature Extraction to Handle Facial Categorization," PLoS ONE, vol. 7, p. e38478, 2012.
[4] M. Ghodrati, S.-M. Khaligh-Razavi, R. Ebrahimpour, K. Rajaei, and M. Pooyan, "How Can Selection of Biologically Inspired Features Improve the Performance of a Robust Object Recognition Model?," PLoS ONE, vol. 7, p. e32357, 2012.
Project |02
Mining Social Network of Persian Blogosphere - Social Networks Laboratory, School of ECE., University of Tehran, Tehran, Iran, Sep. 2011 – Jan. 2012
​
We studied blogs of Blogfa (The biggest blog service in Persian which most of its bloggers are Iranian people) and their web graph. We also analyzed the websites that cited by these blogs. Based on this study we suggested a method to estimate the content similarity among these websites. Results published later in ASNA 2012.
​
Resources:
Archive, Internet. Heritrix Hmoe Page. n.d. http://crawler.archive.org (accessed July 26, 2012).
[1] B. Etling, J. Kelly, R. Faris, and J. Palfrey, "Mapping the Arabic Blogosphere: Politics, Culture, and Dissent." Berkman Center Research Publication No. 2009-06, 2009.
[2] Bastian M., Heymann S., Jacomy M. "Gephi: an open source software for exploring and manipulating networks." Gephi: an open source software for exploring and manipulating networks. 2009.
[4] Cottle, S. "Media and the Arab uprisings of 2011: Research notes." Journalism, 2011: 647-659.
​
Project |03
Internship – Social Networks Laboratory, School of ECE., University of Tehran, Tehran, Iran.
Developing a Facebook Calendar Application, June 2011 – Aug. 2011
We developed an application for Iranian users of Facebook for collecting their information and using them for future social network analysis tasks we have in our Lab.