AI development for healthcare aims to enhance medical decision-making through risk evaluation. Scholars have focused on improving the accuracy of Breast Cancer AI Risk Assessment Tools (BC-AIRAT), yet these tools remain underutilized in clinical practices. This provides an opportunity to explore how these tools are used and how they may support risk communications. We conducted a three-phase study, with clinicians and patients, in the context of the United States healthcare system, including formative interviews that surface the challenges of BC-AIRAT practices, design probe re-purposing BC-AIRAT as supporting risk communications, and design probe-driven interviews with diverse stakeholders. Our findings surface the gap and opportunity for designing AI-mediated risk communication tool, highlighting the participants’ reflections on AI for managing risk assessment workflows, mediating fragmented breast health guidelines, and delivering information to patients for proactive decision making. We conclude with design implications for using AI as a mediator in breast cancer risk communication.

Equity is crucial to the ethical implications in technology development. However, implementing equity in practice comes with complexities and nuances. In response, the research community, especially the human-computer interaction (HCI) and Fairness community, has endeavored to integrate equity into technology design, addressing issues of societal inequities. With such increasing efforts, it is yet unclear why and how researchers discuss equity and its integration into technology, what research has been conducted, and what gaps need to be addressed. We conducted a systematic literature review on equity and technology, collecting and analyzing 202 papers published in HCI and Fairness-focused venues. Amidst the substantial growth of relevant publications within the past four years, we deliver three main contributions: (1) we elaborate a comprehensive understanding researchers' motivations for studying equity and technology, (2) we illustrate the different equity definitions and frameworks utilized to discuss equity, (3) we characterize the key themes addressing interventions as well as tensions and trade-offs when advancing and integrating equity to technology. Based on our findings, we elaborate an equity framework for researchers who seek to address existing gaps and advance equity in technology.

Public sector agencies aim to innovate not just for efficiency but also to enhance equity. Despite the growing adoption of data-driven decision-making systems in the public sector, efforts to integrate equity as a primary goal often fall short. This typically arises from inadequate early-stage involvement of underserved stakeholders and prevalent misunderstandings concerning the authentic meaning of equity from these stakeholders' perspectives. Our research seeks to address this gap by actively involving undersevered stakeholders in the process of envisioning the integration of equity within public sector data-driven decisions, particularly in the context of a building department in a Northeastern mid-sized U.S. city. Applying a speed dating method with storyboards, we explore diverse equity-centric futures within the realm of local business development, a domain where small businesses, particularly women-and minority-owned businesses, historically confront inequitable distribution of public services. We explored three essential aspects of equity: monitoring equity, resource allocation prioritization, as well as information and equity. Our findings illuminate the complexities of integrating equity into data-driven decisions, offering nuanced insights about the needs of stakeholders. We found that attempts to monitor and incorporate equity goals into public sector decision-making can unexpectedly backfire, inadvertently sparking community apprehension and potentially exacerbating existing inequities. Small business owners, including those identifying as women-and minority-owned, advocated against the use of demographic-based data in equity-focused data-driven decision-making in the public sector, instead emphasizing factors such as community needs, application complexity, and uncertainties inherent in small businesses. Drawing from these insights, we propose design implications to assist designers of public sector data-driven decision-making systems to better accommodate equity considerations.

Because anomalous samples cannot be used for training, many anomaly detection and localization methods use pre-trained networks and non-parametric modeling to estimate encoded feature distribution. However, these methods neglect the impact of position and neighborhood information on the distribution of normal features. To overcome this, we propose a new algorithm, PNI, which estimates the normal distribution using conditional probability given neighborhood features, modeled with a multi-layer perceptron network. Moreover, position information is utilized by creating a histogram of representative features at each position. Instead of simply resizing the anomaly map, the proposed method employs an additional refine network trained on synthetic anomaly images to better interpolate and account for the shape and edge of the input image. We conducted experiments on the MVTec AD benchmark dataset and achieved state-of-the-art performance, with 99.56% and 98.98% AUROC scores in anomaly detection and localization, respectively. Code is available at https://github.com/wogur110/PNI_Anomaly_Detection.

There have been many image denoisers using deep neural networks, which outperform conventional model-based methods by large margins. Recently, self-supervised methods have attracted attention because constructing a large real noise dataset for supervised training is an enormous burden. The most representative self-supervised denoisers are based on blind-spot networks, which exclude the receptive field’s center pixel. However, excluding any input pixel is abandoning some information, especially when the input pixel at the corresponding output position is excluded. In addition, a standard blind-spot network fails to reduce real camera noise due to the pixel-wise correlation of noise, though it successfully removes independently distributed synthetic noise. Hence, to realize a more practical denoiser, we propose a novel self-supervised training framework that can remove real noise. For this, we derive the theoretic upper bound of a supervised loss where the network is guided by the downsampled blinded output. Also, we design a conditional blind-spot network (C-BSN), which selectively controls the blindness of the network to use the center pixel information. Furthermore, we exploit a random subsampler to decorrelate noise spatially, making the C-BSN free of visual artifacts that were often seen in downsample-based methods. Extensive experiments show that the proposed C-BSN achieves state-of-the-art performance on real-world datasets as a self-supervised denoiser and shows qualitatively pleasing results without any post-processing or refinement.

Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in the high-frequency region, giving equal consideration to the low and high-frequency areas. In this paper, we propose a new lossless image compression method that proceeds the encoding in a coarse-to-fine manner to separate and process low and high-frequency regions differently. We initially compress the low-frequency components and then use them as additional input for encoding the remaining high-frequency region. The low-frequency components act as a strong prior in this case, which leads to improved estimation in the high-frequency area. In addition, we design the frequency decomposition process to be adptive to color channel, spatial location, and image characteristics. As a result, our method derives an image-specific optimal ratio of low/high-frequency components. Experiments show that the proposed method achieves state-of-the-art performance for benchmark high-resolution datasets.

As robots become more ubiquitous across human spaces, it is becoming increasingly relevant for researchers to ask the question, “how can we ensure that we are designing robots to be sufficiently equipped to treat people fairly?”. This workshop brings together researchers across the fields of Human-Robot Interaction (HRI), fairness in machine learning, design, and transparency in AI to shed light on the relevant methodological challenges surrounding issues of fairness and transparency in HRI. In our workshop, we will attempt to identify synergies between these various fields. In particular, we will focus on how HRI can leverage these existing rich body of work to guide the formalization of fairness metrics and methodologies. Another goal of the workshop is to foster a community of interdisciplinary researchers to encourage collaboration. The complexity in defining fairness lies in its context sensitive nature, as such we look to the influx of definitions from the field of fairness in artificial intelligence, design, and organizational psychology to derive a set of definitions that could serve as guidelines for researchers in HRI.

In this paper, we present EatingTrak, an AI-powered sensing system using a wrist-mounted inertial measurement unit (IMU) to recognize eating moments in a near-free-living semi-wild setup. It significantly improves the SOTA in time resolution using similar hardware on identifying eating moments, from over five minutes to three seconds. Different from prior work which directly learns from raw IMU data, it proposes intelligent algorithms which can estimate the arm posture in 3D in the wild and then learns the detailed eating moments from the series of estimated arm postures. To evaluate the system, we collected eating activity data from 9 participants in semi-wild scenarios for over 113 hours. Results showed that it was able to recognize eating moments at three time-resolutions: 3 seconds and 15 minutes with F-1 scores of 73.7% and 83.8%, respectively. EatingTrak would introduce new opportunities in sensing detailed eating behavior information requiring high time resolution, such as eating frequency, snack-taking, on-site behavior intervention. We also discuss the opportunities and challenges in deploying EatingTrak on commodity devices at scale.

Given a time-evolving tensor stream with missing values, how can we accurately discover latent factors in an online manner to predict missing values? Online tensor factorization is a crucial task with many important applications including the analysis of climate, network traffic, and epidemic disease. However, existing online methods have disregarded temporal locality and thus have limited accuracy.

This paper presents a channel-wise progressive coding system for lossless compression of color images. We follow the classical lossless compression scheme of LOCO-I and CALIC, where pixel values and coding contexts are predicted and forwarded to the entropy coder for compression. The contribution is that we jointly estimate the pixel values and coding contexts from neighboring pixels by training a simple multilayer perceptron in a residual and channel-wise progressive manner. Specifically, we obtain accurate pixel prediction along with coding contexts that reflect the magnitude of local activity very well. These results are sent to an adaptive arithmetic coder that appropriately encodes the prediction error according to the corresponding coding context. Experimental results demonstrate the effectiveness of the proposed method in high-resolution datasets.

This paper presents an encoder for the lossless compression of color filter array (CFA) data, which consists of a hierarchical predictor and context-adaptive arithmetic encoder. In hierarchical prediction, the subsampled images are encoded in order; each of the subimages contains only one color component (red, green, or blue) in the case of a Bayer CFA image. By subsampling, the green pixels are separated into two sets, one of which is encoded by a conventional grayscale encoder, and then is used to predict the green pixels in the other set. Both the sets of greens are then used to predict the reds, and the green and red pixels are used to predict the blues. Throughout this process, the predictors are designed considering the direction of the edges in the neighborhood. By gathering some information from the prediction process, such as edge activity and neighboring errors, the magnitude of prediction error is also estimated. From this, the probability distribution function of prediction error conditioned on neighboring pixels, i.e., the context is estimated, and context-adaptive arithmetic encoding is applied to reduce the resulting bits further. The experimental results on real and simulated CFA images show that the proposed method produces less bits per pixel than the conventional lossless image compression methods and recently developed lossless CFA compression algorithms.

This paper presents a new lossless color image compression algorithm, based on the hierarchical prediction and context-adaptive arithmetic coding. For the lossless compression of an RGB image, it is first decorrelated by a reversible color transform and then Y component is encoded by a conventional lossless grayscale image compression method. For encoding the chrominance images, we develop a hierarchical scheme that enables the use of upper, left, and lower pixels for the pixel prediction, whereas the conventional raster scan prediction methods use upper and left pixels. An appropriate context model for the prediction error is also defined and the arithmetic coding is applied to the error signal corresponding to each context. For several sets of images, it is shown that the proposed method further reduces the bit rates compared with JPEG2000 and JPEG-XR.

This paper proposes a new feature-based image registration method based on the description of feature clusters. This method can find larger number of correspondences than the conventional methods using singleton feature descriptors, which often fail in repetitive patterns. The reason for the failure of conventional methods in a repeating pattern is due to the existence of too many similar features, which in turn gives geometrically inconsistent matching or do not survive ratio test. Hence the proposed method follows the strategy that first separate the similar features from the repetitive patterns from the others. Then the similar features in a pattern are grouped into a set that is described by a support vector descriptor in terms of the cluster's center and radius. Once the same pattern in different images are matched, the geometric cue is added to find many geometrically consistent correspondences of the features. In the experiments, it has been demonstrated that the larger number of geometrically consistent correspondences from the repetitive pattern give more accurate registration, and thus more pleasing results in image stitching and panoramic image generation.

In many conventional lossless color image compression methods, the pixels or lines from each color component are interleaved, and then they are predicted and coded. Also, it has been reported that the reversible color transform (RCT) followed by a grayscale encoder gives higher coding gain than the independent compression of each channel does. In this paper, we propose a lossless color image compression method that concentrates on the efficient coding of chrominance channels with a new color transform and hierarchical coding of chrominance channel pixels. Specifically, we first transform an input image with R, G, and B color space into Y CuCvcolor space using the proposed RCT, which shows better decorrelation performance than the existing RCT. After the color transformation, the luminance channel Y is compressed by a conventional lossless image coder, such as JPEG-LS, CALIC, or JPEG2000 lossless. Unlike the luminance channel, the chrominance channels Cuand Cvare relatively smooth and have different statistical characteristic. Therefore, the chrominance channels are differently encoded based on a hierarchical decomposition and directional prediction. Finally, effective context modeling for prediction residuals is adopted. Experimental results show that the proposed method improves the compression performance by 40% over the conventional channel independent compression methods and 5% over the existing methods that exploit the channel correlation.

This paper proposes a new color filter array de-mosaicking method with emphasis on the edge estimation. In many existing approaches, the demosaicking is considered a directional interpolation problem, and thus finding the correct edge direction is a very important factor. However, these methods sometimes fail to determine an accurate interpolating direction because they use local information from neighboring pixels. For the estimation of edge direction using global information, we employ an MRF framework where the energy function is formulated by defining new notions of interpolation risk and pixel connectivity. Minimizing this function gives the edge directions, and the green channel is interpolated along the edges. Then we iterate the luminance update and color correction using the high frequencies from green channel. The algorithm is tested with the commonly used images, and it is shown to yield higher CPSNR than the state-of-the-art methods in many images, up to 2.7dB at maximum and 0.4dB on average. Subjective comparison also shows that the proposed method produces less artifacts on complex structures.

This paper describes a DSP integration of sound source localization (SSL) and multi-channel Wiener filter (MWF). To develop a robot audition system, we integrated SSL module and MWF module into a DSP system. SSL is a module to perceive the direction of a human user's call. It measures time delay of arrival among microphones and estimates the direction of sound source. Also, it post-processes the resulted estimations of direction by histogram to perceive the direction robustly under noisy environment. MWF is a module to reduce background noises from raw voice signal to enhance the performance of robot's speech recognition. It gathers information of background noises during noise-period and then reduces noises during voice-period. This SSL-MWF combination system will be a cheap, high-performing and convenient solution for robot audition.