The creative sketching partner (CSP) is a proof of concept intelligent interface to inspire designers while in response specified design task. With this interactive system we are studying the effect an AI model visual and conceptual similarity for selecting Al's sketch as inspiration current state user's sketch. Specifically, interested behavior when engaged By developing deep learning models sketches from large-scale dataset, user can control amount requesting CSP. We conducted study with...

Systematic reviews are essential in helping researchers address pre-defined research questions through explicit, methodical, and reproducible techniques for identifying studies comprehensively synthesizing their findings. We highlight our experiences conducting two systematic review HCI: (1) women's reproductive health HCI (2) the intersection of identity older adults research. identify patterns lessons that can be applied to enhance reporting communication While these may not universally...

This paper provides a framework for evaluating creativity in co-creative systems: those that involve computer programs collaborating with human users on creative tasks. We situate systems within broader context of computational and explain the unique qualities these systems. present four main questions can guide evaluation Who is creativity, what being evaluated, when does occur how performed. These provide comparing existing evaluate we apply them to examples art, humor, games robotics....

This paper presents and evaluates a new method for inspiring creativity in co-creative design system. The uses computational model of aconceptual shift based on clustering deep features from database sketches. sketching tool maps user's sketch to distinct category that has high, medium, or low visual semantic similarity. We hypothesize the degree similarity between system's sketches is associated with range cognitive models context. report findings an empirical study analyzes different...

This paper presents a computational model for conceptual shifts, based on novelty metric applied to vector representation generated through deep learning. is integrated into co-creative design system, which enables partnership between an AI agent and human designer interacting sketching canvas. The responds the designer's sketch with new that shift: intentionally varying visual similarity increasingly more novelty. results of user study showing increasing in contribution associated higher...

Recalling medical instructions provided during a doctor's visit can be difficult due to access barriers, primarily for older adults who doctors multiple times per year and rely on their memory act recommendations. There are several interventions that aid patients in recalling information after doctors' visits; however, some have been proven ineffective, those effective present additional challenges adults. In this paper, we explore the with chronic illnesses face when collecting from visits...

In this innovative practice full paper, we address the equity gap for neurodivergent and situationally limited learners by identifying spectrum of dynamic factors that impact learning function. Educators have shown a growing interest in learners' cognitive abilities preferences to measure their on academic achievement. Often institutions employ one-size-fits-all approaches leaving burden disabled students self-advocate or tolerate inadequate support. Emerging frameworks guide through...

We present a system for identifying conceptual shifts between visual categories, which will form the basis co-creative drawing to help users draw more creative sketches. The recognizes human sketches and matches them structurally similar from categories they do not belong. This would allow produce an ambiguous sketch that blends features both categories.

Despite growing interest in accessible texting for people who are blind and visually impaired (BVI), little is known about the practice of when on move, especially while using assistive technologies. To address this gap, we conducted an interview-based study with 20 BVIs text travelling. Our findings revealed that participants engage outside their home four recurrent situations: walking to a destination, waiting public transportation, riding vehicle, or approaching point interest. Moreover,...

During doctor's visits, the medical conversations shared often contain essential instructions and tailored advice necessary for daily care, particularly among older adults who manage chronic illnesses. However, some adult patients face barriers accessibility challenges that limits their access to information. Current research improve provided during patient-physician focuses on methods such as one-to-one sessions can be applied visit but are not available after session ends. Electronic...

Accurate pedestrian detection has an important role in automotive applications because, by issuing warnings to the driver and acting actively on car brakes, it can save human lives decrease probability of injuries. In order achieve adequate accuracy, detectors require training sets containing a very large number negative samples, which be challenging for algorithms models like support vector machines (SVM). A common approach deal with such datasets is Hard Negative Mining (HNM), avoids...

Texting relies on screen-centric prompts designed for sighted users, still posing significant barriers to people who are blind and visually impaired (BVI). Can we re-imagine texting untethered from a visual display? In an interview study, 20 BVI adults shared situations surrounding their practices, recurrent topics of conversations, challenges. Informed by these insights, introduce TextFlow: mixed-initiative context-aware system that generates entirely auditory message options relevant the...

Texting relies on screen-centric prompts designed for sighted users, still posing significant barriers to people who are blind and visually impaired (BVI). Can we re-imagine texting untethered from a visual display? In an interview study, 20 BVI adults shared situations surrounding their practices, recurrent topics of conversations, challenges. Informed by these insights, introduce TextFlow , mixed-initiative context-aware system that generates entirely auditory message options relevant the...