output
19972026
most citedFault-tolerant quantum computation by anyons

7.3k citations

Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026★ 1 cited

A Self-Supervised Pose Estimation Approach for Construction Machines

Alaa Alshubbak, Daniel Görges

Pose estimation is a computer vision task used to estimate a skeleton of dynamic systems to predict future movements. Most of the research in this direction is based on a supervise…

cs.CV2025★ 6 cited

Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models

Marcel Rogge, Didier Stricker

Current Gaussian Splatting approaches are effective for reconstructing entire scenes but lack the option to target specific objects, making them computationally expensive and unsui…

cs.CV2024★ 2 cited

Webcam-based Pupil Diameter Prediction Benefits from Upscaling

Vijul Shah, Brian B. Moser, Ko Watanabe +1

Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye da…

cs.CV2024★ 12 cited

ContextMix: A context-aware data augmentation method for industrial visual inspection systems

Hyungmin Kim, Donghun Kim, Pyunghwan Ahn +3

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These…

cs.CV2023★ 1 cited

MeciFace: Mechanomyography and Inertial Fusion-based Glasses for Edge Real-Time Recognition of Facial and Eating Activities

Hymalai Bello, Sungho Suh, Bo Zhou +1

The increasing prevalence of stress-related eating behaviors and their impact on overall health highlights the importance of effective and ubiquitous monitoring systems. In this pa…

cs.CV2023★ 6 cited

PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulation

Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh +1

Ground pressure exerted by the human body is a valuable source of information for human activity recognition (HAR) in unobtrusive pervasive sensing. While data collection from pres…

cs.CV2021★ 4 cited

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut -Tree Representation

Sk Aziz Ali, Kerem Kahraman, Gerd Reis +1

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel -tree representation for the input point…