Debugging is a crucial skill for any new programmer to learn. Writing AND debugging code can be too challenging for students, so this assignment seeks to make the debugger more approachable by using it as a terminal-based debugging game. The ''game'' is a simulation of a Clue-style Murder Mystery story, which is completely randomized based on each student's login ID. The MurderMystery driver will run the simulation, and then ask students a series of questions about the events of the simulation. Students can answer these via the terminal, and then submit the auto-generated Answers file to be auto-graded by the GameResults auto-grader. The questions range in type and scope, requiring anything from a single normal breakpoint, up to four conditional breakpoints to answer. The students must use the variable viewer in the debugger to inspect nested object structures and access certain coordinates of 2D arrays. Since each student's mystery is randomized, it required a slightly different approach for everyone, while still sharing similar tactics. By introducing the debugger in this way, students can approach the task as a game to be solved, with lower stakes than if they were trying to fix their own code. While still providing familiarity with the debugger, boolean conditions, simple object structures, and more.

Many organizations have embraced the "Lakehouse" data management paradigm, which involves constructing structured data warehouses on top of open, unstructured data lakes. This approach stands in stark contrast to traditional, closed, relational databases and introduces challenges for performance and stability of distributed query processors. Firstly, in large-scale, open Lakehouses with uncurated data, high ingestion rates, external tables, or deeply nested schemas, it is often costly or wasteful to maintain perfect and up-to-date table and column statistics. Secondly, inherently imperfect cardinality estimates with conjunctive predicates, joins and user-defined functions can lead to bad query plans. Thirdly, for the sheer magnitude of data involved, strictly relying on static query plan decisions can result in performance and stability issues such as excessive data movement, substantial disk spillage, or high memory pressure. To address these challenges, this paper presents our design, implementation, evaluation and practice of the Adaptive Query Execution (AQE) framework, which exploits natural execution pipeline breakers in query plans to collect accurate statistics and re-optimize them at runtime for both performance and robustness. In the TPC-DS benchmark, the technique demonstrates up to 25× per query speedup. At Databricks, AQE has been successfully deployed in production for multiple years. It powers billions of queries and ETL jobs to process exabytes of data per day, through key enterprise products such as Databricks Runtime, Databricks SQL, and Delta Live Tables.

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system relies on a deep learning front-end to detect 3D objects from a given RGB frame and associate them to a global object-based map using a graph neural network (GNN). Based on these frame-to-model associations, our back-end optimizes object bounding volumes, represented as super-quadrics, under multi-view geometry constraints and the object scale prior. We validate the proposed system on ScanNet where we show a significant improvement over existing RGB-only methods.

We present a personalized, comprehensive eye-tracking solution based on tracking higher-order Purkinje images, suited explicitly for eyeglasses-style AR and VR displays. Existing eye-tracking systems for near-eye applications are typically designed to work for an on-axis configuration and rely on pupil center and corneal reflections (PCCR) to estimate gaze with an accuracy of only about 0.5°to 1°. These are often expensive, bulky in form factor, and fail to estimate monocular accommodation, which is crucial for focus adjustment within the AR glasses.Our system independently measures the binocular vergence and monocular accommodation using higher-order Purkinje reflections from the eye, extending the PCCR based methods. We demonstrate that these reflections are sensitive to both gaze rotation and lens accommodation and model the Purkinje images' behavior in simulation. We also design and fabricate a user-customized eye tracker using cheap off-the-shelf cameras and LEDs. We use an end-to-end convolutional neural network (CNN) for calibrating the eye tracker for the individual user, allowing for robust and simultaneous estimation of vergence and accommodation. Experimental results show that our solution, specifically catering to individual users, outperforms state-of-the-art methods for vergence and depth estimation, achieving an accuracy of 0.3782° and 1.108cm respectively.

High-quality computer vision models typically address the problem of understanding the general distribution of real-world images. However, most cameras observe only a very small fraction of this distribution. This offers the possibility of achieving more efficient inference by specializing compact, low-cost models to the specific distribution of frames observed by a single camera. In this paper, we employ the technique of model distillation (supervising a low-cost student model using the output of a high-cost teacher) to specialize accurate, low-cost semantic segmentation models to a target video stream. Rather than learn a specialized student model on offline data from the video stream, we train the student in an online fashion on the live video, intermittently running the teacher to provide a target for learning. Online model distillation yields semantic segmentation models that closely approximate their Mask R-CNN teacher with 7 to 17× lower inference runtime cost (11 to 26× in FLOPs), even when the target video's distribution is non-stationary. Our method requires no offline pretraining on the target video stream, achieves higher accuracy and lower cost than solutions based on flow or video object segmentation, and can exhibit better temporal stability than the original teacher. We also provide a new video dataset for evaluating the efficiency of inference over long running video streams.

Relative attribute models can compare images in terms of all detected properties or attributes, exhaustively predicting which image is fancier, more natural, and so on without any regard to ordering. However, when humans compare images, certain differences will naturally stick out and come to mind first. These most noticeable differences, or prominent differences, are likely to be described first. In addition, many differences, although present, may not be mentioned at all. In this work, we introduce and model prominent differences, a rich new functionality for comparing images. We collect instance-level annotations of most noticeable differences, and build a model trained on relative attribute features that predicts prominent differences for unseen pairs. We test our model on the challenging UT-Zap50K shoes and LFW10 faces datasets, and outperform an array of baseline methods. We then demonstrate how our prominence model improves two vision tasks, image search and description generation, enabling more natural communication between people and vision systems.

Smartphone sensors are becoming more universal and more accurate. In this paper, we aim to distinguish between four common positions or states a phone can be in: in the hand, pocket, backpack, or on a table. Using a uniquely designed neural network and data from the accelerometer and the screen state, we achieve a 92% accuracy on the same phone. We also explore extending this to different phones and propose an acceleration calibration technique to do so.

Augmented reality (AR) presentations may be visual or auditory. Auditory presentation has the potential to provide hands-free and visually non-obstructing cues. Recently, we have developed a 3D audio wearable system that can be used to provide alerts and informational cues to a mobile user in such a manner as to appear to emanate from specific locations in the user's environment. In order to study registration errors in 3D audio AR representations, we conducted a perceptual training experiment in which visual and auditory cues were presented to observers. The results of this experiment suggest that perceived registration errors may be reduced through head movement and through training presentations that include both visual and auditory cues.