Chris Thomas

chris_thomas_photo.jpg

378 Data and Decision Sciences Building

727 Prices Fork Rd

Blacksburg, VA 24060

(540) 231-2993

I am an Assistant Professor in the Department of Computer Science at Virginia Tech. My research is in computer vision. I am interested in many problems requiring reasoning across multimodal data, such as cross-modal retrieval, high-level content understanding, and multimodal knowledge representation. I am associated with the Sanghani Center for Artificial Intelligence and Data Analytics.

Prior to joining Virginia Tech, I was a postdoctoral researcher at Columbia University working with Professor Shih-Fu Chang. I received my Ph.D. in Computer Science from the Department of Computer Science at the University of Pittsburgh in 2020. My advisor was Professor Adriana Kovashka.

Note: I am currently recruiting strong and motivated students to join our growing group! Please visit the Prospective Students page for details.

Recent News

Feb 2024 Our work on defending vision-language models against adversarial attacks was accepted to CVPR 2024.
Dec 2023 Our paper on predicting cross-modal event relations was accepted to AAAI 2024
Nov 2023 Our work on fine-grained multidocument multimodal inconsistency checking was featured in Columbia Engineering Magazine (“When Trust Is a Factor”)
May 2023 Awarded CVPR 2023 Outstanding Reviewer
Jul 2022 Our paper on fine-grained visual entailment was accepted to ECCV 2022
Jun 2022 Our journal article on using weak caption supervision for object detection was accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)

Selected Publications

  1. Fine-Grained Visual Entailment
    Christopher Thomas, Yipeng Zhang, and Shih-Fu Chang
    In Proceedings of the European Conference on Computer Vision, 2022
  2. InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection
    Yi Fung, Christopher Thomas, Revanth Reddy, and 6 more authors
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), 2021
  3. Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval
    Christopher Thomas, and Adriana Kovashka
    In Proceedings of the European Conference on Computer Vision (ECCV), 2020
  4. Predicting the politics of an image using webly supervised data
    Christopher Thomas, and Adriana Kovashka
    In Advances in Neural Information Processing Systems (NeurIPS 2019), 2019