Rahmatri Mardiko

Graduate Student
email: mardiko at cs dot umd dot edu

I am a third year PhD student at the Department of Computer Science, University of Maryland, College Park. My research interest is in the intersection of Computer Vision and Human Computer Interaction. I work under the supervision of Professor Larry Davis and Assistant Professor Tom Yeh of University of Colorado, Boulder. I obtained my Bachelor and Master's degree from Faculty of Computer Science, Universitas Indonesia.

In the past, I worked on multiple objects tracking for video surveillance under the supervision of M. Rahmat Widyanto. We wrote the following articles.

Mardiko, R., & Widyanto, M. R. (2009, April). An Approach to Object Counting for Video Surveillance Using Fuzzy Inference System with Fault Tolerance. In Proc. Intl Conf on IT Application and Management, UI Depok.
Mardiko, R., & Widyanto, M. R. (2013). Resolving Occlusion in Multi-Object Tracking through Integrated Fuzzy Similarity Measure. International Journal of Video & Image Processing & Network Security, 13(5). (PDF)

I also worked with Prof. T. Basaruddin on still images and video watermarking under the graduate research grant from the Ministry of Education. We wrote two articles at national venues (both were written in Bahasa Indonesia).

Mardiko, R., & Basaruddin, T. (2009). Watermarking pada Video: Robustness, Impercetibility dan Pendekatan untuk Domain Terkompresi. In Proceedings of Konferensi Nasional Teknologi Informasi dan Aplikasi. Universitas Sriwijaya.(PDF)
Mardiko, R., & Basaruddin, T. (2011). Evaluasi Skema Watermarking Citra Berbasis SVD, Kuantisasi Dither, dan Deteksi Sisi. MAKARA of Science Series, 14(2). (PDF)

As a graduate student at University of Maryland, I was fortunate to work with Tom Yeh (was a postdoc at UMD) and Katharina Reinecke (was a postdoc at Harvard) on predicting user's impression of web aesthetic. I helped in the computer vision/images analysis part of the work.

Reinecke, K., Yeh, T., Miratrix, L., Mardiko, R., Zhao, Y., Liu, J., & Gajos, K. Z. (2013, April). Predicting users' first impressions of website aesthetics with a quantification of perceived visual complexity and colorfulness. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 2049-2058). ACM. (PDF)

Now, I have decided to work on another interesting problem in the intersection of computer vision and human computer interaction.

"I am working on the analysis of images from social media to help people build better situation awareness during times of crisis. To this day there hasn't been much work done to get useful information related to events from user-generated images despite of its richness in information. The problem of images analysis from social media is hard due to unconstrained nature of the contents. The goal of my research is to develop a computer vision algorithm for organizing the images based on the proximity in visual and spatio-temporal features. The result will be helpful for gaining better situation awareness through the enhanced images browsing and navigation."