Related papers: PhysLab: A Benchmark Dataset for Multi-Granularity…

While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models…

The educational use of video and multimedia is increasing rapidly in secondary and higher education across all disciplines. Videos for physics education can be found in many universities and other educational institutions websites all over…

Short-video platforms show an increasing impact on people's daily lives nowadays, with billions of active users spending plenty of time each day. The interactions between users and online platforms give rise to many scientific problems…

Object recognition has made great advances in the last decade, but predominately still relies on many high-quality training examples per object category. In contrast, learning new objects from only a few examples could enable many impactful…

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for…

Current large-scale video datasets focus on general human activity, but lack depth of coverage on fine-grained activities needed to address physical skill learning. We introduce SportSkills, the first large-scale sports dataset geared…

Marker-less 3D human motion capture from a single colour camera has seen significant progress. However, it is a very challenging and severely ill-posed problem. In consequence, even the most accurate state-of-the-art approaches have…

Physics problem-solving is a challenging domain for AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Existing evaluations fail to capture the full breadth and…

Recent advancements in deep learning, computer vision, and embodied AI have given rise to synthetic causal reasoning video datasets. These datasets facilitate the development of AI algorithms that can reason about physical interactions…

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…

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…

Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding,…

In order for AI to be safely deployed in real-world scenarios such as hospitals, schools, and the workplace, it must be able to robustly reason about the physical world. Fundamental to this reasoning is physical common sense: understanding…

Deep learning has shown remarkable progress in a wide range of problems. However, efficient training of such models requires large-scale datasets, and getting annotations for such datasets can be challenging and costly. In this work, we…

We release two artificial datasets, Simulated Flying Shapes and Simulated Planar Manipulator that allow to test the learning ability of video processing systems. In particular, the dataset is meant as a tool which allows to easily assess…

While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion, a dataset and benchmark for rigorously evaluating the…

Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this…

While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce…

Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We…

Object grasping is critical for many applications, which is also a challenging computer vision problem. However, for the clustered scene, current researches suffer from the problems of insufficient training data and the lacking of…