Related papers: CaptainCook4D: A Dataset for Understanding Errors …
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our…
Choreographers determine what the dances look like, while cameramen determine the final presentation of dances. Recently, various methods and datasets have showcased the feasibility of dance synthesis. However, camera movement synthesis…
Recent advancements in protein structure determination are revolutionizing our understanding of proteins. Still, a significant gap remains in the availability of comprehensive datasets that focus on the dynamics of proteins, which are…
Many everyday tasks, ranging from appliance repair and cooking to car maintenance, require expert knowledge, particularly for complex, multi-step procedures. Despite growing interest in AI agents for augmented reality (AR) assistance,…
How can an end-user provide feedback if a deployed structured prediction model generates inconsistent output, ignoring the structural complexity of human language? This is an emerging topic with recent progress in synthetic or constrained…
We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through open-form language instructions. Previous large-scale editing…
How do two individuals differ when performing the same action? In this work, we introduce Video Action Differencing (VidDiff), the novel task of identifying subtle differences between videos of the same action, which has many applications,…
In many cases an intelligent agent may want to learn how to mimic a single observed demonstrated trajectory. In this work we consider how to perform such procedural learning from observation, which could help to enable agents to better use…
The enormous progress in the field of artificial intelligence (AI) enables retail companies to automate their processes and thus to save costs. Thereby, many AI-based automation approaches are based on machine learning and computer vision.…
Improved surgical skill is generally associated with improved patient outcomes, although assessment is subjective; labour-intensive; and requires domain specific expertise. Automated data driven metrics can alleviate these difficulties, as…
Audio-Driven Face Animation is an eagerly anticipated technique for applications such as VR/AR, games, and movie making. With the rapid development of 3D engines, there is an increasing demand for driving 3D faces with audio. However,…
This paper provides guidance for building and maintaining infrastructure for participatory AI efforts by sharing reflections on building World Wide Dishes (WWD), a bottom-up, community-led image and text dataset of culinary dishes and…
Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions. However, existing datasets are often limited to specific tasks, small scale, and lack the…
Skill assessment in procedural videos is crucial for the objective evaluation of human performance in settings such as manufacturing and procedural daily tasks. Current research on skill assessment has predominantly focused on sports and…
We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions…
Monitoring dietary habits is crucial for preventing health risks associated with overeating and undereating, including obesity, diabetes, and cardiovascular diseases. Traditional methods for tracking food intake rely on self-reported data…
This paper addresses the challenge of classifying and assigning programming tasks to experts, a process that typically requires significant effort, time, and cost. To tackle this issue, a novel dataset containing a total of 4,112…
Cooking requires not only following instructions but also understanding, executing, and monitoring each step - a process that can be challenging without visual guidance. Although recipe images and videos offer helpful cues, they often lack…
Reliable procedural monitoring in video requires exposure to naturally occurring human errors and the recoveries that follow. In egocentric recordings, mistakes are often partially occluded by hands and revealed through subtle object state…
Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and motor demands. But current benchmarks are often limited by small scale, unimodal sensing or…