Ph.D.​ The University of North Carolina at Chapel Hill, 2015M.S. Stony Brook University (SUNY), 2013​Eng. Escuela Superior Politécnica del Litoral, 2008

"Our group builds systems that can describe visual information using natural language and learn to do so efficiently from large amounts of data."

Vicente Ordonez-Roman, Assistant Professor


Research interests include:

Computer Vision, Machine Learning, Natural Language Processing



Please visit the academic webpage that I actively maintain:

I'm Assistant Professor in the Department of Computer Science at the University of Virginia. I also spent a year as visiting research fellow at the Allen Institute for Artificial Intelligence (AI2) n the Computer Vision group. My research lies at the intersection of Computer Vision, Natural Language Processing and Machine Learning. I am especially interested in analyzing, and mining useful human insights from enormous amounts of images with associated text. I am also interested in big scale visual analytics by learning models that can perform high-level perceptual tasks for applications in social media, urban computing, and everyday activities. I'm a recipient of the 2013 IEEE Marr Prize in Computer Vision, Best Long Paper Award at EMNLP 2017, and Faculty Awards from Google, Facebook, and IBM.


  • NSF CAREER Award 2021
  • Facebook Research Award 2020
  • Google Faculty Research Award 2017
  • IBM Faculty Award 2017
  • EMNLP Best Paper Award 2017
  • IEEE Marr Prize -- ICCV Best Paper Award 2013
  • Yahoo Key Scientific Challenges Award 2012

Research Interests

  • Computer Vision
  • Machine Learning
  • Natural Language Processing

Selected Publications

  • Face Recognition Technologies in the Wild: A Call for a Federal Office. Whitepaper. May 2020. ABS Erik Learned-Miller, Vicente Ordóñez Román, Jamie Morgenstern, Joy Buolamwini
  • Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries. Conf. on Neural Information Processing Systems. NeurIPS 2019. Vancouver, Canada. ABS Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo, Hui Wu, Song Feng, Vicente Ordonez
  • Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations. International Conference on Computer Vision. ICCV 2019. Seoul, South Korea ABS Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez
  • Text2Scene: Generating Compositional Scenes from Textual Descriptions. Conference on Computer Vision and Pattern Recognition. CVPR 2019. Long Beach, California. ABS Fuwen Tan, Song Feng, Vicente Ordonez
  • Feedback-prop: Convolutional Neural Network Inference under Partial Evidence. CVPR 2018. Salt Lake City, Utah. ABS Tianlu Wang, Kota Yamaguchi, Vicente Ordonez.
  • Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints (Best Long Paper Award). Conference on Empirical Methods in Natural Language Processing. EMNLP 2017. Copenhagen, Denmark. ABS Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang.
  • Commonly Uncommon: Semantic Sparsity in Situation Recognition. Intl. Conference on Computer Vision and Pattern Recognition. CVPR 2017. Honolulu, Hawaii. July 2017. ABS Mark Yatskar, Vicente Ordonez, Luke Zettlemoyer Ali Farhadi.
  • XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. European Conference on Computer Vision. ECCV 2016. Amsterdam, The Netherlands. October 2016. ABS Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi.
  • From Large Scale Image Categorization to Entry-Level Categories (Marr Prize, Best Paper Award). IEEE International Conference on Computer Vision. ICCV 2013. Sydney, Australia. December 2013. ABS Vicente Ordonez, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg.