Large Language Models (LLMs) have shown strong performance in translating natural language into programming languages like Python or Java. However, for niche computer languages, where there is limited training data, fine-tuning a base model is often necessary. A key challenge arises when the pretrained embeddings of natural language terms interfere with the intended syntax and semantics of formal language terms. This issue is especially pronounced in the logical language of SUO-KIF, which is used in the Suggested Upper Merged Ontology (SUMO). SUMO contains thousands of terms that closely resemble everyday English words. As a result, models often produce syntactic errors or hallucinate non-existent terms due to conflicting embeddings learned during base training. This work introduces a tokenization-based technique to mitigate these issues. By altering how formal terms are tokenized, we can decouple their embeddings from similar natural language words, significantly reducing syntax errors and term hallucinations in the generated formal language output.

Recent work on video stream fingerprinting has begun to explore its effectiveness in large open-world scenarios, in which the vast majority of test samples are from unmonitored videos that are unknown to the model at training time, showing that it is more difficult than earlier small open-world results have suggested. However, the evaluated approach employed deep learning techniques with potential shortcomings for the open-world task. We build on that work to evaluate more advanced techniques drawn from the literature on open set recognition, out-of-distribution detection, and robustness to adversarial examples, hypothesizing that they can improve effectiveness. We find that combinations of techniques can improve effectiveness, cutting the open-world false positive rate by up to 92% at a recall of 0.5. However, precision would likely still be problematic at the full-scale of the largest platforms hosting hundreds of millions or more videos. Additionally, we find that introducing two other dimensions of realism - when training and test sets are streamed from different vantage points, and when monitoring shorter videos or traffic flows - can greatly increase open-world false positives, making the full-scale open-world task even more difficult. Accordingly, we call for more work to focus on larger and more realistic open-world scenarios to continue to gain a better understanding of the effective envelope for fingerprinting.

Despite the recent flight control regulations, Unmanned Aerial Vehicles (UAVs) are still gaining popularity in civilian and military applications, as much as for personal use. Such emerging interest is pushing the development of effective collision avoidance systems. Such systems play a critical role UAVs operations especially in a crowded airspace setting. Because of cost and weight limitations associated with UAVs payload, camera based technologies are the de-facto choice for collision avoidance navigation systems. This requires multi-target detection and tracking algorithms from a video, which can be run on board efficiently. While there has been a great deal of research on object detection and tracking from a stationary camera, few have attempted to detect and track small UAVs from a moving camera. In this paper, we present a new approach to detect and track UAVs from a single camera mounted on a different UAV. Initially, we estimate background motions via a perspective transformation model and then identify distinctive points in the background subtracted image. We find spatio-temporal traits of each moving object through optical flow matching and then classify those candidate targets based on their motion patterns compared with the background. The performance is boosted through Kalman filter tracking. This results in temporal consistency among the candidate detections. The algorithm was validated on video datasets taken from a UAV. Results show that our algorithm can effectively detect and track small UAVs with limited computing resources.

The TRECVID report of 2010 [14] evaluated video shot boundary detectors as achieving "excellent performance on [hard] cuts and gradual transitions." Unfortunately, while re-evaluating the state of the art of the shot boundary detection, we found that they need to be improved because the characteristics of consumer-produced videos have changed significantly since the introduction of mobile gadgets, such as smartphones, tablets and outdoor activity purposed cameras, and video editing software has been evolving rapidly. In this paper, we evaluate the best-known approach on a contemporary, publicly accessible corpus, and present a method that achieves better performance, particularly on soft transitions. Our method combines color histograms with key point feature matching to extract comprehensive frame information. Two similarity metrics, one for individual frames and one for sets of frames, are defined based on graph cuts. These metrics are formed into temporal feature vectors on which a SVM is trained to perform the final segmentation. The evaluation on said "modern" corpus of relatively short videos yields a performance of 92% recall (at 89% precision) overall, compared to 69% (91%) of the best-known method.

Model generation for virtual and augmented reality environments is cumbersome, time consuming, and difficult. We present methods for rapidly texturing registered geometry and for quickly creating environment maps. The video from a tracked camera is projected onto the geometry and cached within the geometry's textures. Object appearance thus becomes persistent beyond its momentary exposure to the video. The algorithms run in real-time and can be applied to arbitrary geometry

Tracking hands in live video is a challenging task: the hand appearance can change too rapidly for appearance-based trackers to work, and color-based trackers (that do not rely on geometry) have to make limiting assumptions about the background color. This article shows the results of hand tracking with "Flocks of Features", a tracking method that combines motion cues and a learned foreground color distribution to achieve fast and robust 2D tracking of highly articulated objects. Many independent image artifacts are tracked from one frame to the next, adhering only to local constraints. This concept is borrowed from nature since these tracks mimic the flight of flocking birds - exhibiting local individualism and variability while maintaining a clustered entirety. Hand tracking has important applications for interaction with wearable computers, for intuitive manipulation of virtual objects, for detection of activity signatures, and much more. Tracking with Flocks of Features is not limited to hands - any articulated or appearance-changing object can benefit from this multi-cue tracking method.

Vision-based user interfaces are a feasible and advantageous modality for wearable computers. To substantiate this claim, we present a robust real-time hand gesture recognition system that is capable of being the sole input provider for a demonstration application. It achieves usability and interactivity even when both the head-worn camera and the object of interest are in motion. We describe a set of general gesture-based interaction styles and explore their characteristics in terms of task suitability and the computer vision algorithms required for their recognition. Preliminary evaluation of our prototype system leads to the conclusion that vision-based interfaces have achieved the maturity necessary to help overcome some limitations of more traditional mobile user interfaces.