Related papers: Improving students' understanding of rotating fram…

Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity…

In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning…

Many physics instructors aim to support student sensemaking in their classrooms. However, this can be challenging since instances of sensemaking tend to be short-lived, with students often defaulting to approaches based on answer-making or…

Object pose estimation is a core perception task that enables, for example, object grasping and scene understanding. The widely available, inexpensive and high-resolution RGB sensors and CNNs that allow for fast inference based on this…

In a recent report, the American Association of Physics Teachers has developed an updated set of recommendations for curriculum of undergraduate physics labs.1 This document focuses on six major themes: constructing knowledge, modeling,…

We study student behavior and performance in two Massive Open Online Courses (MOOCs). In doing so, we present two frameworks by which video-watching clickstreams can be represented: one based on the sequence of events created, and another…

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.…

In two earlier studies, we developed a new method to measure students' ability to transfer physics problem solving skills to new contexts using a sequence of online learning modules, and implemented two interventions in the form of…

We aim to enable robot to learn object manipulation by imitation. Given external observations of demonstrations on object manipulations, we believe that two underlying problems to address in learning by imitation is 1) segment a given…

Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence…

Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant…

The set of polarizing force-identification (PFI) questions in the FCI consists of six items all basically asking only one question: the set of forces acting on a given body. Although it may sound trivial, these questions are among the most…

The ability to categorize problems based upon underlying principles, rather than surface features or contexts, is considered one of several proxy predictors of expertise in problem solving. With inspiration from the classic study by Chi,…

In this study, we adapt prior identity framework to investigate the effect of learning environment (including perceived recognition, peer interaction and sense of belonging) on students' physics self-efficacy, interest and identity by…

This paper reports on an investigation into the correlations between students' understandings of introductory astronomy concepts and the correctness and coherency of their written responses to targeted Lecture-Tutorial questions. We…

Estimating 3D rotations is a common procedure for 3D computer vision. The accuracy depends heavily on the rotation representation. One form of representation -- rotation matrices -- is popular due to its continuity, especially for pose…

Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively…

We find equations of particle motion from the point of view of observer on a rotating disk, and demonstrate that a particle moving along a rotating disk is influenced by forces arising from geometry. They can be considered as analogs of the…

Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets has shown that models…

3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…