Computer Vision is a field concerned with enabling computers with the ability to understand the visual world much like humans do with their visual system. Image data acquired by camera sensors are processed according to computational models specifically developed, and that allow interpreting the structure, appearance, semantics and dynamics of the objects in the scene. Computer vision technology is used extensively in areas such as robotics, autonomous driving, virtual and augmented reality, industrial manufacturing, biometrics, healthcare, and many others. The future of this technology is to develop novel approaches that further integrate with machine leaning and artificial intelligence for the purpose of automating and integrating higher level vision and action tasks in a robust and explainable manner. This will allow, for instance, not only to trust driving autonomous vehicles, but also to speed up and reduce the cost of healthcare by leveraging automated medical diagnoses tools.
Affiliated Faculty
Recent Publications
- Stanislav Pidhorskyi, Donald A Adjeroh, Gianfranco Doretto, “Adversarial Latent Autoencoders,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14104-14113, 2020 June 14-19, 2020, Seattle, Washington.
- Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi, “Exploiting Joint Robustness to Adversarial Perturbations,” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 14-19, 2020, Seattle, Washington.
- Chen Zhao, Zhiguo Cao, Chi Li, Xin Li, Jiaqi Yan, “NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 215-224, 2019.