TA.L409.3
An Inter-observer consistent deep adversarial training for visual scanpath prediction
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, University of Orleans, France; Alessandro Bruno, IULM University, Italy
Session:
TA.L409: Quality Assessment I Lecture
Track:
Image and Video Sensing, Modeling, and Representation
Location:
Room 409
Presentation Time:
Tue, 10 Oct, 11:36 - 11:54 Malaysia Time (UTC +8)
Session Chair:
Chaker Larabi, Université de Poitiers
Session TA.L409
TA.L409.1: HALF OF AN IMAGE IS ENOUGH FOR QUALITY ASSESSMENT
Junyong You, NORCE Norwegian Research Centre, Norway; Yuan Lin, Kristiania University College, Norway; Jari Korhonen, University of Aberdeen, United Kingdom of Great Britain and Northern Ireland
TA.L409.2: MTJND: MULTI-TASK DEEP LEARNING FRAMEWORK FOR IMPROVED JND PREDICTION
Sanaz Nami, Tampere University, University of Tehran, Finland; Farhad Pakdaman, Tampere University, Finland; Mahmoud Reza Hashemi, University of Tehran, Iran (Islamic Republic of); Shervin Shirmohammadi, University of Ottawa, Canada; Moncef Gabbouj, Tampere University, Finland
TA.L409.3: An Inter-observer consistent deep adversarial training for visual scanpath prediction
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, University of Orleans, France; Alessandro Bruno, IULM University, Italy
TA.L409.4: PRE-TRAINING WITH FRACTAL IMAGES FACILITATES LEARNED IMAGE QUALITY ESTIMATION
Malte Silbernagel, Thomas Wiegand, Peter Eisert, Sebastian Bosse, Fraunhofer Heinrich-Hertz-Institute, Germany
TA.L409.5: A Multiscale Approach to Deep Blind Image Quality Assessment
Manni Liu, South China University of Technology, China; Jiabin Huang, Xiamen University, China; Delu Zeng, South China University of Technology, China; XingHao Ding, Xiamen University, China; John Paisley, Columbia University, United States of America
Contacts