Related papers: Using Tracker as a Pedagogical Tool for Understand…

In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…

Projection pursuit is used to find interesting low-dimensional projections of high-dimensional data by optimizing an index over all possible projections. Most indexes have been developed to detect departure from known distributions, such as…

Real-time online object tracking in videos constitutes a core task in computer vision, with wide-ranging applications including video surveillance, motion capture, and robotics. Deployed tracking systems usually lack formal safety…

Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to class-incremental…

Kinematics is a core topic in early physics courses, yet students often struggle to interpret motion and its graphical representations. To tackle these difficulties, we developed MissionMotion, a physical-computational videogame where…

Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology…

To deepen do-it-yourself (DIY) technology in the physics classroom, we seek to highlight the Open Source Physics (OSP) community of educators that engage, enable and empower teachers as learners so that we create DIY technology…

Incorporating computer programming exercises in introductory physics is a delicate task that involves a number of choices that may have a strong affect on student learning. We present an approach that speaks to a number of common concerns…

This study focuses on evaluating three methods used to determine the theoretical gravity in the city of Cusco and their importance in distance education. The first method is based on Newton's law of universal gravitation, obtaining a…

Incorporating computer programming exercises into introductory physics is a delicate task that involves a number of choices that may have an effect on student learning. We present a "hybrid" approach that speaks to a number of common…

Motion tracking has been an important technique for imitating human-like movement from large-scale datasets in physics-based motion synthesis. However, existing approaches focus on tracking either single character or a particular type of…

Motion models play a great role in visual tracking applications for predicting the possible locations of objects in the next frame. Unlike target tracking in radar or aerospace domain which considers only points, object tracking in computer…

Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do…

Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously…

The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few…

A common hope of many physics educators and researchers is that students leave the course with a stronger sense that physics is relevant to them than when they entered the course. Multiple survey measures have attempted to measure shifts in…

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling…

Understanding human-object interactions is fundamental in First Person Vision (FPV). Tracking algorithms which follow the objects manipulated by the camera wearer can provide useful cues to effectively model such interactions. Despite a few…

Flipped learning is a method that flips in/out class activities to make lectures learner-centered. In flipped learning, comments from learners on preparation material are useful information for instructors to consider before deciding…