Associate Professor MBZUAI
Computer Vision Department
Fahad Khan is currently an Associate Professor at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). Fahad Khan actively works on deep neural networks, towards detailed visual understanding and learning visual recognition models with limited supervision. His research includes applications to a wide range of topics within computer vision: object recognition, detection, segmentation, tracking and action recognition.
Please visit his Google Scholar profile, for more details about Fahad Khan’s research work.
My research field is computer vision. My research covers a wide range of topics within computer vision, including object recognition, detection, tracking, segmentation, and human action recognition in images and videos. My focus is on learning visual recognition models with limited human supervision. A massive and ever growing amount of digital content (images and videos) is available today. To address queries about such massive data, it is impractical to learn visual models by manually annotating every relevant concept, object, or action category in a representative sample of everyday situations. The aim is to develop novel visual recognition models that can efficiently scale to a large number of concepts without explicitly relying on spoon-fed supervision and data.
- Two papers accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). [April’21]
- Five papers (including one Oral) accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [March’21]
- Five papers accepted at European Conference on Computer Vision (ECCV). [Jul’20]
- Nine papers (including three Oral) accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [March’20]
- I am a course co-ordinator for Human and Computer Vision course (ML701) at MBZUAI (Spring 2021).
- I will be teaching Visual Object Recognition and Detection course (CV703) in the Fall at MBZUAI.