Related papers: Enhancing Kinematics Understanding through a Video…
Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds. We focus on the challenging real-world problem of action-graph extraction from material science papers, where language is highly…
Motion prediction systems aim to capture the future behavior of traffic scenarios enabling autonomous vehicles to perform safe and efficient planning. The evolution of these scenarios is highly uncertain and depends on the interactions of…
Transfer of learning is an important objective of education. However, students usually have difficulties in solving physics transfer tasks even after having solved similar problems previously. We investigated if instruction provided using…
Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly…
Automatic surgical gesture recognition is fundamentally important to enable intelligent cognitive assistance in robotic surgery. With recent advancement in robot-assisted minimally invasive surgery, rich information including surgical…
Massive Open Online Courses (MOOCs) have become increasingly popular worldwide. However, learners primarily rely on watching videos, easily losing knowledge context and reducing learning effectiveness. We propose HyperMOOC, a novel approach…
In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal…
Studies of human cognition often rely on brief, highly controlled tasks that emphasize group-level effects but poorly capture the rich variability within and between individuals. A suite of minigames built on the novel pixelDOPA platform…
Pedestrian dynamics models have provided valuable insights into pedestrian interactions, collision avoidance, and self-organized crowd behavior using mathematical, computational, AI-based, and heuristic approaches. However, existing models…
As mobile technologies have become ubiquitous in recent years, computer-based cognitive tests have become more popular and efficient. In this work, we focus on assessing motor function in children by analyzing their gait movements. Although…
On public benchmarks, current action recognition techniques have achieved great success. However, when used in real-world applications, e.g. sport analysis, which requires the capability of parsing an activity into phases and…
Gamification initiatives are currently top-of-mind for many organizations seeking to engage their employees in creative ways, improve their productivity, and drive positive behavioural outcomes in their workforce - ultimately leading to…
Promotion of healthy habits help maintain and improve people health, reduce disease risks, and manage chronic illness. Regular healthy activities like walking, exercising, healthy eating, drinking water or taking medication on time require…
We contribute a first design space on visualizations in motion and the design of a pilot study we plan to run in the fall. Visualizations can be useful in contexts where either the observation is in motion or the whole visualization is…
Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion. While human athletes can effectively perceive environmental characteristics to select appropriate footholds for obstacle traversal, endowing legged…
Children tend to be constantly exposed to technologies, such as smartphones, tablets, and gaming consoles, drawn by the interactive and visually stimulating nature of digital platforms. Thus, integrating the teaching process with…
Quantum mechanics courses focus mostly on its computational aspects. This alone does not provide the same depth of understanding as most physicists have of classical mechanics. The understanding of classical mechanics is significantly…
We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks. Using several instantiations of the dataset in which variation is explicitly controlled, we highlight issues in…
In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment to answer a situated question with confidence. This problem remains challenging in robotics, due to the difficulties in…