Pairwise comparison data arise in many domains with subjective assessment experiments,
for example in image and video quality assessment. In these experiments observers are …

In this paper we present a hybrid active sampling strategy for pairwise preference
aggregation, which aims at recovering the underlying rating of the test candidates from …

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to
new tasks by leveraging contextual information contained in in-context examples to enhance …

To assess the quality of multimedia content, create datasets, and train objective quality
metrics, one needs to collect subjective opinions from annotators. Different subjective …

The goal of most subjective studies is to place a set of stimuli on a perceptual scale. This is
mostly done directly by rating, eg using single or double stimulus methodologies, or …

Cellular sheaves are a discrete model for the theory of sheaves on cell complexes. They
carry a canonical cochain complex computing their cohomology. This thesis develops the …

Subjective image quality assessment studies are used in many scenarios, such as the
evaluation of compression, super-resolution, and denoising solutions. Among the available …

To gather larger datasets to train data-angry deep learning quality assessment models,
crowdsourcing has become essential to recruit participants. These participants are asked …

The development of rigorous quality assessment model relies on the collection of reliable
subjective data, where the perceived quality of visual multimedia is rated by the human …

This paper contains the research proposal of Andréas Pastor that was presented at the
MMSys 2022 doctoral symposium. Encoding video for streaming on Internet has become a …