Zoya’s work lies at the interface of human perception & cognition, computer vision & machine learning, and human computer interfaces. Zoya actively works on understanding and modeling human attention and memory, as well as on artificial intelligence for creativity. She is excited by the concept of “visual symbolism”: how humans successfully communicate complex and often abstract topics through visual means, in designing information visualizations, infographics, iconography, and graphic designs. Zoya’s approach to research is to run perception studies on humans, and use the collected insights to build smarter computational algorithms. Zoya’s work is interdisciplinary and is published in top-tier human vision, computer vision, HCI, and visualization venues.

Zoya received her PhD from MIT in 2018, advised by Dr. Fredo Durand (computer graphics) and Dr. Aude Oliva (perception and cognition) at the Computer Science and Artificial Intelligence Lab. Her thesis was on “Computational Perception for Multimodal Document Understanding” and was awarded the George M. Sprowls Award for Best PhD Theses in Computer Science. Zoya’s M.Sc. thesis, also from MIT, titled “Computational Understanding of Image Memorability” was supervised by Dr. Antonio Torralba and Dr. Aude Oliva. Prior to this, Zoya attended the University of Toronto, where she majored in computer science and statistics and was an undergraduate research assistant in computer vision, working on parts-based object recognition and sign language understanding. More on Zoya’s research can be found here: http://web.mit.edu/zoya/www/research.html.

A complete list of publications can be found on Google Scholar. The below list is incomplete, and only includes papers published since joining Adobe in 2018.


Parsing and Summarizing Infographics with Synthetically Trained Icon Detection

Madan, S., Bylinskii, Z., Nobre, C., Tancik, M., Recasens, A., Zhong, K., Alsheikh, S., Oliva, A., Durand, F., Pfister, H. (May. 25, 2021)

IEEE Pacific Visualization Symposium (PacificVis)

Leveraging Text-Chart Links to Support Authoring of Data-Driven Articles with VizFlow

Sultanum, N., Chevalier, F., Bylinskii, Z., Liu, L. (May. 13, 2021)

ACM Conference on Human Factors in Computing Systems (CHI)

Mitigating the Effects of Reading Interruptions by Providing Reviews and Previews

Srivastava, N., Jain, R., Healey, J., Bylinskii, Z., Dingler, T. (May. 8, 2021)

ACM CHI Conference on Human Factors in Computing Systems Extended Abstracts (CHI'EA)

Toward Quantifying Ambiguities in Artistic Images

Wang, X., Bylinskii, Z., Hertzmann, A., Pepperell, R. (Nov. 6, 2020)

ACM Transactions on Applied Perception (TAP)

Predicting Visual Importance Across Graphic Design Types

Fosco, C., Casser, V., Bedi, A., O'Donovan, P., Hertzmann, A., Bylinskii, Z. (Oct. 20, 2020)

ACM Symposium on User Interface Software and Technology (UIST)

Look here! A parametric learning based approach to redirect visual attention

Mejjati, Y., Gomes, C., Kim, K., Shechtman, E., Bylinskii, Z. (Aug. 23, 2020)

European Conference on Computer Vision (ECCV)

TurkEyes: A Web-Based Toolbox for Crowdsourcing Attention Data

Newman, A., McNamara, B., Fosco, C., Bin Zhang, Y., Sukhum, P., Tancik, M., Kim, N., Bylinskii, Z. (Apr. 25, 2020)

ACM Conference on Human Factors in Computing Systems (CHI)

ICONATE: Automatic Compound Icon Generation and Ideation

Zhao, N., Kim, N., Herman, L., Pfister, H., Lau, R., Echevarria, J., Bylinskii, Z. (Apr. 25, 2020)

ACM Conference on Human Factors in Computing Systems (CHI)

Accelerating Adult Readers with Typeface: A Study of Individual Preferences and Effectiveness

Wallace, S., Treitman, R., Huang, J., Sawyer, B., Bylinskii, Z. (Apr. 25, 2020)

ACM CHI Conference on Human Factors in Computing Systems Extended Abstracts (CHI'EA)

How much time do you have? Modeling multi-duration saliency

Fosco, C., Newman, A., Sukhum, P., Bin Zhang, Y., Zhao, N., Oliva, A., Bylinskii, Z. (Mar. 30, 2020)

Computer Vision and Pattern Recognition (CVPR)

How Many Glances? Modeling Multi-duration Saliency

Fosco, C., Newman, A., Sukhum, P., Bin Zhang, Y., Oliva, A., Bylinskii, Z. (Dec. 13, 2019)

Workshop on Shared Visual Representations in Human and Machine Intelligence at NeurIPS (SVRHM)