Related papers: Simitate: A Hybrid Imitation Learning Benchmark
Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…
We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…
This study, conducted among more than 250 physics and chemistry teachers in Morocco, analyzes the impact of experimentation on student learning and attention in middle and high school. The results show that the majority of teachers favor…
Teaching robots dexterous manipulation skills often requires collecting hundreds of demonstrations using wearables or teleoperation, a process that is challenging to scale. Videos of human-object interactions are easier to collect and…
Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…
Understanding action correspondence between humans and robots is essential for evaluating alignment in decision-making, particularly in human-robot collaboration and imitation learning within unstructured environments. We propose a…
In the complex manufacturing sector a considerable amount of resources are focused on developing new skills and training workers. In that context, increasing the effectiveness of those processes and reducing the investment required is an…
In this paper, we introduce RoboLight, the first real-world robotic manipulation dataset capturing synchronized episodes under systematically varied lighting conditions. RoboLight consists of two components. (a) RoboLight-Real contains…
It remains a question that how simultaneous interpretation (SI) data affects simultaneous machine translation (SiMT). Research has been limited due to the lack of a large-scale training corpus. In this work, we aim to fill in the gap by…
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark for evaluating…
Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast). These post-processing techniques vary across manufacturers and are generally kept proprietary,…
Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently,…
Low-light videos often exhibit spatiotemporal incoherent noise, leading to poor visibility and compromised performance across various computer vision applications. One significant challenge in enhancing such content using modern…
We present Human Motions with Objects (HUMOTO), a high-fidelity dataset of human-object interactions for motion generation, computer vision, and robotics applications. Featuring 735 sequences (7,875 seconds at 30 fps), HUMOTO captures…
Photorealistic color retouching plays a vital role in visual content creation, yet manual retouching remains inaccessible to non-experts due to its reliance on specialized expertise. Reference-based methods offer a promising alternative by…
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a…
Previous studies have suggested that being imitated by an adult is an effective intervention with children with autism and developmental delay. The purpose of this study is to investigate if an imitation game with a robot can arise interest…
We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry…
Learning from demonstrations in the wild (e.g. YouTube videos) is a tantalizing goal in imitation learning. However, for this goal to be achieved, imitation learning algorithms must deal with the fact that the demonstrators and learners may…
Rigging and skinning are essential steps to create realistic 3D animations, often requiring significant expertise and manual effort. Traditional attempts at automating these processes rely heavily on geometric heuristics and often struggle…