Search for: All records

Zero-shot learning (ZSL) addresses the unseen class recognition problem by leveraging semantic information to transfer knowledge from seen classes to unseen classes. Generative models synthesize the unseen visual features and convert ZSL into a classical supervised learning problem. These generative models are trained using the seen classes and are expected to implicitly transfer the knowledge from seen to unseen classes. However, their performance is stymied by overfitting, which leads to substandard performance on Generalized Zero-Shot learning (GZSL). To address this concern, we propose the novel LsrGAN, a generative model that Leverages the Semantic Relationship between seen and unseen categories and explicitly performs knowledge transfer by incorporating a novel Semantic Regularized Loss (SR-Loss). The SR-loss guides the LsrGAN to generate visual features that mirror the semantic relationships between seen and unseen classes. Experiments on seven benchmark datasets, including the challenging Wikipedia text-based CUB and NABirds splits, and Attribute-based AWA, CUB, and SUN, demonstrates the superiority of the LsrGAN compared to previous state-of-the-art approaches under both ZSL and GZSL. Code is available at https://github.com/Maunil/LsrGAN. 

For the significant global population of individuals who are blind or visually impaired, spatial awareness during navigation remains a challenge. Tactile Electronic Travel Aids have been designed to assist with the provision of spatiotemporal information, but an intuitive method for mapping this information to patterns on a vibrotactile display remains to be determined. This paper explores the encoding of distance from a navigator to an object using two strategies: absolute and relative. A wearable prototype, the HapBack, is presented with two straps of vertically aligned vibrotactile motors mapped to five distances, with each distance mapped to a row on the display. Absolute patterns emit a single vibration at the row corresponding to a distance, while relative patterns emit a sequence of vibrations starting from the bottom row and ending at the row mapped to that distance. These two encoding strategies are comparatively evaluated for identification accuracy and perceived intuitiveness of mapping among ten adult participants who are blind or visually impaired. No significant difference was found between the intuitiveness of the two encodings based on these metrics, with each showing promising results for application during navigation tasks. 

Given that most cues exchanged during a social interaction are nonverbal (e.g., facial expressions, hand gestures, body language), individuals who are blind are at a social disadvantage compared to their sighted peers. Very little work has explored sensory augmentation in the context of social assistive aids for individuals who are blind. The purpose of this study is to explore the following questions related to visual-to-vibrotactile mapping of facial action units (the building blocks of facial expressions): (1) How well can individuals who are blind recognize tactile facial action units compared to those who are sighted? (2) How well can individuals who are blind recognize emotions from tactile facial action units compared to those who are sighted? These questions are explored in a preliminary pilot test using absolute identification tasks in which participants learn and recognize vibrotactile stimulations presented through the Haptic Chair, a custom vibrotactile display embedded on the back of a chair. Study results show that individuals who are blind are able to recognize tactile facial action units as well as those who are sighted. These results hint at the potential for tactile facial action units to augment and expand access to social interactions for individuals who are blind.