- M. Mahdavi, M. Condon, K. Davila, and R. Zanibbi (2019)
**LPGA: Line-of-Sight Parsing with Graph-Based Attention for Math Formula Recognition**. *Proc. International Conference on Document Analysis and Recognition*, Sydney, Australia (to appear). - M. Mahdavi, R. Zanibbi, H. Mouchere, and Utpal Garain (2019). ICDAR 2019 CROHME + TFD: Competition on Recognition of Handwritten Mathematical Expressions and Typeset Formula Detection.
*Proc. International Conference on Document Analysis and Recognition, *Sydney, Australia (to appear). - M. Mahdavi and R. Zanibbi (2019) Tree-Based Structure Recognition Evaluation for Math Expressions: Techniques and Case Study.
** ***IAPR Graphics Recognition Workshop (at ICDAR 2019)*, Sydney, Australia (to appear). - M. Mahdavi, M. Condon, and R. Zanibbi (2018) Applying Hierarchical Contextual Parsing to Isolated Typeset Math Formulas.
*Western New York Image Processing Workshop (WNYIP)*, Rochester, NY, USA. (poster).

- Mansouri, B., Rohatgi, S., Oard, D., Wu, J., Giles, C.L., and Zanibbi, R. (2019)
**Tangent-CFT: An Embedding model for Mathematical Formulas**. *Proc. International Conference on the Theory of Information Retrieval*. Santa Clara, California, USA (*to appear*). - Mansouri, B., and Oard, D., and Zanibbi, R. (2019) Characterizing Searches for Mathematical Concepts,
* Proc. Joint Conference on Digital Libraries, Urbana-Champaign*, Illinois, USA.

- Zhong, W. and Zanibbi, R. (2019) Structural Similarity Search for Formulas using Leaf-Root Paths in Operator Subtrees.
*Proc. European Conference on Information Retrieval*, Cologne, Germany (**Best Applications Paper Award**). - Davila, K. and Zanibbi, R. (2019) Tangent-V: Math Formula Image Search Using Line-of-Sight Graphs.
*Proc. European Conference on Information Retrieval*, Cologne, Germany. - Davila, K. and Zanibbi, R. (2018) Visual Search Engine for Handwritten and Typeset Math in Lecture Videos and LaTeX Notes.
*Proc. Int'l Conf. Frontiers in Handwriting Recognition*, Niagara Falls, NY (**Best Paper Award**).

###
MathSeer is supported by the Alfred P. Sloan Foundation and the National Science Foundation