Helping Visually Impaired People Take Better Quality Pictures.

Perception-based image analysis technologies can be used to help visually impaired people take better quality pictures by providing automated guidance, thereby empowering them to interact more confidently on social media. The photographs taken by visually impaired users often suffer from one or both of two kinds of quality issues: technical quality (distortions), and semantic quality, such as framing and aesthetic composition. Here we develop tools to help them minimize occurrences of common technical distortions, such as blur, poor exposure, and noise. We do not address the complementary problems of semantic quality, leaving that aspect for future work. The problem of assessing, and providing actionable feedback on the technical quality of pictures captured by visually impaired users is hard enough, owing to the severe, commingled distortions that often occur. To advance progress on the problem of analyzing and measuring the technical quality of visually impaired user-generated content (VI-UGC), we built a very large and unique subjective image quality and distortion dataset. This new perceptual resource, which we call the LIVE-Meta VI-UGC Database, contains 40K real-world distorted VI-UGC images and 40K patches, on which we recorded 2.7M human perceptual quality judgments and 2.7M distortion labels. Using this psychometric resource we also created an automatic limited vision picture quality and distortion predictor that learns local-to-global spatial quality relationships, achieving state-of-the-art prediction performance on VI-UGC pictures, significantly outperforming existing picture quality models on this unique class of distorted picture data. We also created a prototype feedback system that helps to guide users to mitigate quality issues and take better quality pictures, by creating a multi-task learning framework. The dataset and models can be accessed at: https://github.com/mandal-cv/visimpaired.

A Perspective on Building Ethical Datasets for Children's Conversational Agents.

Artificial intelligence (AI)-powered technologies are becoming an integral part of youth's environments, impacting how they socialize and learn. Children (12 years of age and younger) often interact with AI through conversational agents (e.g., Siri and Alexa) that they speak with to receive information about the world. Conversational agents can mimic human social interactions, and it is important to develop socially intelligent agents appropriate for younger populations. Yet it is often unclear what data are curated to power many of these systems. This article applies a sociocultural developmental approach to examine child-centric intelligent conversational agents, including an overview of how children's development influences their social learning in the world and how that relates to AI. Examples are presented that reflect potential data types available for training AI models to generate children's conversational agents' speech. The ethical implications for building different datasets and training models using them are discussed as well as future directions for the use of social AI-driven technology for children.

Hierarchical partial matching and segmentation of interacting cells.

We propose a method that automatically tracks and segments living cells in phase-contrast image sequences, especially for cells that deform and interact with each other or clutter. We formulate the problem as a many-to-one elastic partial matching problem between closed curves. We introduce Double Cyclic Dynamic Time Warping for the scenario where a collision event yields a single boundary that encloses multiple touching cells and that needs to be cut into separate cell boundaries. The resulting individual boundaries may consist of segments to be connected to produce closed curves that match well with the individual cell boundaries before the collision event. We show how to convert this partial-curve matching problem into a shortest path problem that we then solve efficiently by reusing the computed shortest path tree. We also use our shortest path algorithm to fill the gaps between the segments of the target curves. Quantitative results demonstrate the benefit of our method by showing maintained accurate recognition of individual cell boundaries across 8068 images containing multiple cell interactions.