One of the primary goals of introductory programming courses is to develop fundamental programming competencies, including the ability to design and implement computer programs. Computer-based laboratory examinations, or lab exams, are considered a valid, efficient, and reliable assessment method for these competencies. In a lab exam, students are required to complete programming tasks in a proctored and time-limited setting with measures to prevent academic dishonesty. However, the proliferation of Generative Artificial Intelligence (GenAI) has raised new challenges for academic integrity during lab exams. In this work, we propose an approach to selectively block common GenAI tools during lab exams and share our preliminary experience using it in an introductory programming course.

Ensuring the fairness of machine learning (ML) systems for individuals with disabilities is crucial. Proactive measures are required to identify and mitigate biases in data and models, thereby preventing potential harm or bias against people with disabilities. While previous research on ML fairness education primarily concentrated on gender and race fairness, the domain of disability fairness has received comparatively little attention. Addressing this gap, we adopted a student-centric approach to craft a disability fairness teaching intervention. A focus group of students experienced in ML and accessible computing underscored the significance of engagement and scaffolding strategies for effectively learning intricate topics. Consequently, we crafted a disability fairness hands-on programming assignment that delves into uncovering disability bias with a lens that takes intersectionality into account. The assignment was tailored for an introductory undergraduate data science (DS) course. We employed reflective questions and surveys to gauge the effectiveness of our approach. The findings indicate the success of our approach in promoting a deeper understanding of disability fairness within the context of DS education.

Key aspects of international policy, such as those pertaining to migration and trade, manifest in the physical world at international political borders; for this reason, borders are of interest to political science studying the impacts and implications of these policies. While some prior efforts have worked to characterize features of borders using trained human coders and crowdsourcing, these are limited in scale by the need for manual annotations. In this paper, we present a new task, dataset, and baseline approaches for estimating the legibility of international political borders automatically and on a global scale. Our contributions are to (1) define the border legibility estimation task; (2) collect a dataset of overhead (aerial) imagery for the entire world’s international borders, (3) propose several classical and deep-learning-based approaches to establish a baseline for the task, and (4) evaluate our algorithms against a validation dataset of crowdsourced legibility comparisons. Our results on this challenging task confirm that while low-level features can often explain border legibility, mid- and high-level features are also important. Finally, we show preliminary results of a global analysis of legibility, confirming some of the political and geographic influences of legibility.

What can we learn about a scene by watching it for months or years? A video recorded over a long timespan will depict interesting phenomena at multiple timescales, but identifying and viewing them presents a challenge. The video is too long to watch in full, and some things are too slow to experience in real-time, such as glacial retreat or the gradual shift from summer to fall. Timelapse videography is a common approach to summarizing long videos and visualizing slow timescales. However, a timelapse is limited to a single chosen temporal frequency, and often appears flickery due to aliasing. Also, the length of the timelapse video is directly tied to its temporal resolution, which necessitates tradeoffs between those two facets. In this paper, we propose Video Temporal Pyramids, a technique that addresses these limitations and expands the possibilities for visualizing the passage of time. Inspired by spatial image pyramids from computer vision, we developed an algorithm that builds video pyramids in the temporal domain. Each level of a Video Temporal Pyramid visualizes a different timescale; for instance, videos from the monthly timescale are usually good for visualizing seasonal changes, while videos from the one-minute timescale are best for visualizing sunrise or the movement of clouds across the sky. To help explore the different pyramid levels, we also propose a Video Spectrogram to visualize the amount of activity across the entire pyramid, providing a holistic overview of the scene dynamics and the ability to explore and discover phenomena across time and timescales. To demonstrate our approach, we have built Video Temporal Pyramids from ten outdoor scenes, each containing months or years of data. We compare Video Temporal Pyramid layers to naive timelapse and find that our pyramids enable alias-free viewing of longer-term changes. We also demonstrate that the Video Spectrogram facilitates exploration and discovery of phenomena across pyramid levels, by enabling both overview and detail-focused perspectives.

When observing the visual world, temporal phenomena are ubiquitous: people walk, cars drive, rivers flow, clouds drift, and shadows elongate. Some of these, like water splashing and cloud motion, occur over time intervals that are either too short or too long for humans to easily observe. High-speed and timelapse videos provide a popular and compelling way to visualize these phenomena, but many real-world scenes exhibit motions occurring at a variety of rates. Once a framerate is chosen, phenomena at other rates are at best invisible, and at worst create distracting artifacts. In this article, we propose to automatically normalize the pixel-space speed of different motions in an input video to produce a seamless output with spatiotemporally varying framerate. To achieve this, we propose to analyze scenes at different timescales to isolate and analyze motions that occur at vastly different rates. Our method optionally allows a user to specify additional constraints according to artistic preferences. The motion normalized output provides a novel way to compactly visualize the changes occurring in a scene over a broad range of timescales.

Bundle adjustment is the gold standard for refining solutions to geometric computer vision problems. This paper develops an uncertainty visualization technique for bundle adjustment solutions to Structure from Motion problems. Propagating uncertainty through an optimization- from measurement uncertainties to uncertainties in the resulting parameter estimates- is well understood. However, the calculations involved fail numerically for real problems. Often we cope by considering only individual variances, but this ignores the important mutual dependencies between parameters. The dominant modes of uncertainty in most models are large motions involving nearly all parameters at once. These frequently look like flexions, stretchings, and bendings in the overall scene structure. In this paper we present a numerically tractable method for computing dominant eigenvectors of the covariance of a Bundle Adjustment solution. We pay careful attention to the mismatched scales of rotational and translational parameters. Finally, we animate this spectral information. The resulting interactive visualizations (included in the supplemental) give insight into the quality and failure modes of a model. We hope that this work is a step towards broader uncertainty-aware computation for Structure from Motion.

We present a method for computing ambient occlusion (AO) for a stack of images of a Lambertian scene from a fixed viewpoint. Ambient occlusion, a concept common in computer graphics, characterizes the local visibility at a point: it approximates how much light can reach that point from different directions without getting blocked by other geometry. While AO has received surprisingly little attention in vision, we show that it can be approximated using simple, per-pixel statistics over image stacks, based on a simplified image formation model. We use our derived AO measure to compute reflectance and illumination for objects without relying on additional smoothness priors, and demonstrate state-of-the art performance on the MIT Intrinsic Images benchmark. We also demonstrate our method on several synthetic and real scenes, including 3D printed objects with known ground truth geometry.

Modeling the appearance of outdoor scenes from photo collections is challenging because of appearance variation, especially due to illumination. In this paper we present a simple and robust algorithm for estimating illumination properties-shadows and sun direction-from photo collections. These properties are key to a variety of scene modeling applications, including outdoor intrinsic images, realistic 3D scene rendering, and temporally varying (4D) reconstruction. Our shadow detection method uses illumination ratios to analyze lighting independent of camera effects, and determines shadow labels for each 3D point in a reconstruction. These shadow labels can then be used to detect shadow boundaries and estimate sun direction, as well as to compute dense shadow labels in pixel space. We demonstrate our method on large Internet photo collections of scenes, and show that it outperforms prior multi-image shadow detection and sun direction estimation methods.

We present a method for computing ambient occlusion (AO) for a stack of images of a scene from a fixed viewpoint. Ambient occlusion, a concept common in computer graphics, characterizes the local visibility at a point: it approximates how much light can reach that point from different directions without getting blocked by other geometry. While AO has received surprisingly little attention in vision, we show that it can be approximated using simple, per-pixel statistics over image stacks, based on a simplified image formation model. We use our derived AO measure to compute reflectance and illumination for objects without relying on additional smoothness priors, and demonstrate state-of-the art performance on the MIT Intrinsic Images benchmark. We also demonstrate our method on several synthetic and real scenes, including 3D printed objects with known ground truth geometry.