Related papers: Disagreeing about Crocs and socks: Creating profou…

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the…

A recent Science paper (Bushdid et al, 2014)[1] proposed that humans can discriminate between at least a trillion olfactory stimuli. Here we show that this claim is the result of a fragile estimation framework capable of producing nearly…

Understanding why specific items are recommended to users can significantly increase their trust and satisfaction in the system. While neural recommenders have become the state-of-the-art in recent years, the complexity of deep models still…

The need for grounding in language understanding is an active research topic. Previous work has suggested that color perception and color language appear as a suitable test bed to empirically study the problem, given its cognitive…

Questions regarding implicitness, ambiguity and underspecification are crucial for understanding the task validity and ethical concerns of multimodal image+text systems, yet have received little attention to date. This position paper maps…

Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple…

The perception of color is one of the most important aspects of human vision. From an evolutionary perspective, the accurate perception of color is crucial to distinguishing friend from foe, and food from fatal poison. As a result, humans…

In natural scenes and documents, we can find the correlation between a text and its color. For instance, the word, "hot", is often printed in red, while "cold" is often in blue. This correlation can be thought of as a feature that…

The paper addresses the problem of representing ambiguities in a way that allows for monotonic disambiguation and for direct deductive computation. The paper focuses on an extension of the formalism of underspecified DRSs to ambiguities…

Integrated information theory (IIT) argues that the substrate of consciousness is a maximally irreducible complex of units. Together, subsets of the complex specify a cause-effect structure, composed of distinctions and their relations,…

Recommender systems usually learn user interests from various user behaviors, including clicks and post-click behaviors (e.g., like and favorite). However, these behaviors inevitably exhibit popularity bias, leading to some unfairness…

Visualization research often focuses on perceptual accuracy or helping readers interpret key messages. However, we know very little about how chart designs might influence readers' perceptions of the people behind the data. Specifically,…

Recommender systems usually rely on observed user interaction data to build personalized recommendation models, assuming that the observed data reflect user interest. However, user interacting with an item may also due to conformity, the…

Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to rely on and verify state-of-the-art DNN-based systems,…

Art objects can evoke certain emotions. Color is a fundamental element of visual art and plays a significant role in how art is perceived. This paper introduces a novel approach to classifying emotions in art using Fuzzy Sets. We employ a…

We view sorites in terms of stimuli acting upon a system and evoking this system's responses. Supervenience of responses on stimuli implies that they either lack tolerance (i.e., they change in every vicinity of some of the stimuli), or…

The control and integration of distributed, multi-sensor perceptual systems is a complex and challenging problem. The observations or opinions of different sensors are often disparate incomparable and are usually only partial views. Sensor…

The human visual color response is driven by specialized cells called cones, which exist in three types, viz. R, G, and B. Software is developed to simulate how color images are displayed for different types of color blindness. Specified…

Analysis of stochastic processes can be used to engender critical thinking. Quantum dots have a reversible, stochastic transition between luminescent and non-luminescent states. The luminescence intermittency is known as blinking, and is…

Findings from graphical perception can guide visualization recommendation algorithms in identifying effective visualization designs. However, existing algorithms use knowledge from, at best, a few studies, limiting our understanding of how…