Panos Achlioptas

panos@cs.stanford.edu
personal page

Research interests

My research interests lie at the intersection of Computer Vision, Machine Learning, and Natural Language Processing. My area of focus is on designing deep learning models for visual data that emphasize semantic differences among objects, primarily as these are being expressed with natural language.

Recent publications

P. Achlioptas, M. Ovsjanikov, K. Haydarov, M. Elhoseiny and L. Guibas, ArtEmis: Affective Language for Visual Art, Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (Oral).   
P. Achlioptas, A. Abdelreheem, F. Xia, M. Elhoseiny and L. Guibas, ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes, European Conference Computer Vision (ECCV), 2020 (Oral).   
M. Sung, J. Zhenyu, P. Achlioptas, N. Mitra and L. Guibas, DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces, SIGGRAPH Asia, 2020.   
P. Achlioptas, J. Fan, R. Hawkins, N. Goodman, and L. Guibas, ShapeGlot: Learning Language for Shape Differentiation, IEEE International Conference on Computer Vision (ICCV), 2019.   
R. Huang, MJ. Rakotosaona, P. Achlioptas, L. Guibas and M. Ovsjanikov, OperatorNet: Recovering 3D Shapes From Difference Operators, IEEE International Conference on Computer Vision (ICCV), 2019.   
A. Dubrovina, F. Xia, P. Achlioptas, M. Shalah, R. Groscot, and L. Guibas, Composite Shape Modeling via Latent Space Factorization, IEEE International Conference on Computer Vision (ICCV), 2019.   
R. Huang, P. Achlioptas, L. Guibas and M. Ovsjanikov, Limit Shapes: A Tool for Understanding Shape Differences and Variability in 3D Model Collections, Eurographics Symp. on Geometry Processing, (SGP), 2019.   
P. Achlioptas, O. Diamanti, I. Mitliagkas and L. Guibas, Learning Representations and Generative Models for 3D Point Clouds. 35th International Conference on Machine Learning, (ICML), 2018.   
P. Achlioptas, B. Schoelkopf, K. Borgwardt, Two-Locus Association Mapping in Subquadratic Time, ACM SIGKDD, 2011.