Perception-based image analysis technologies can be used to help visuall...
Current dataset collection methods typically scrape large amounts of dat...
Video conferencing, which includes both video and audio content, has
con...
A visual counterfactual explanation replaces image regions in a query im...
This paper presents a novel task together with a new benchmark for detec...
No-reference (NR) perceptual video quality assessment (VQA) is a complex...
Sign Language is the primary means of communication for the majority of ...
Existing models often leverage co-occurrences between objects and their
...
Blind or no-reference (NR) perceptual picture quality prediction is a
di...
Pre-training convolutional neural networks with weakly-supervised and
se...
Current fully-supervised video datasets consist of only a few hundred
th...
Weakly supervised object detection aims at reducing the amount of superv...
Highlight detection has the potential to significantly ease video browsi...
Current top-performing blind perceptual image quality prediction models ...
Most publicly available image quality databases have been created under
...