From Instance-level Recognition to Visual Relationship Detection: Towards Detailed Scene Understanding
Dr. Fahad Khan, faculty member at MBZUAI, UAE and Linköping University, Sweden.
Short Abstract: Recent years have witnessed tremendous progress in various instance-level recognition tasks, including object detection and segmentation. These instance-level problems have numerous applications in robotics, autonomous driving, and surveillance. However, such applications demand a deeper knowledge of scene semantics beyond instance-level recognition, such as the inference of visual relationships between object pairs. In this talk, we will first present our recent results for fundamental instance-level recognition problems of generic object detection, pedestrian detection, and segmentation. We will discuss how the proposed approaches strive to tackle real-world issues of large-scale variations, heavy occlusions, and limited supervision. In the second part of the talk, we will go one step further from instance-level recognition and discuss how to understand interactions between humans and objects.
Short bio: Fahad Khan is currently a faculty member at MBZUAI, UAE and Linköping University, Sweden. He received the M.Sc. degree in Intelligent Systems Design from Chalmers University of Technology, Sweden and a Ph.D. degree in Computer Vision from Computer Vision Center Barcelona and Autonomous University of Barcelona, Spain. From 2012 to 2014, he was a postdoctoral fellow at Computer Vision Laboratory, Linköping University, Sweden. From 2014 to 2018, he was a research fellow at Linköping University, Sweden. In 2018, he was awarded the Docent title in computer vision from Linköping University, Sweden. He has achieved top ranks on various international challenges (Visual Object Tracking VOT: 1st 2014 and 2018, 2nd 2015, 1st 2016; VOT-TIR: 1st 2015 and 2016; OpenCV Tracking: 1st 2015; 1st PASCAL VOC Segmentation and Action Recognition tasks 2010). He received the best paper award in the computer vision track at IEEE ICPR 2016. He has published over 100 reviewed conference papers, journal articles, and book contributions. His research interests include a wide range of topics within computer vision, including object recognition, detection, segmentation, tracking and action recognition.