paper-with-me

Papers

Noise-in, Bias-out: Balanced and Real-time MoCap Solving

2023-09-25 · Georgios Albanis, Nikolaos Zioulis, Spyridon Thermos, Anargyros Chatzitofis, Kostas Kolomvatsos

Real-time optical Motion Capture (MoCap) systems have not benefited from the advances in modern data-driven modeling. In this work we apply machine learning to solve noisy unstructured marker estimates in real-time and deliver robust marker-based MoCap even when using sparse affordable sensors. To achieve this we focus on a number of challenges related to model training, namely the sourcing of training data and their long-tailed distribution. Leveraging representation learning we design a technique for imbalanced regression that requires no additional data or labels and improves the performance of our model in rare and challenging poses. By relying on a unified representation, we show that training such a model is not bound to high-end MoCap training data acquisition, and exploit the advances in marker-less MoCap to acquire the necessary data. Finally, we take a step towards richer and affordable MoCap by adapting a body model-based inverse kinematics solution to account for measurement and inference uncertainty, further improving performance and robustness. Project page: https://moverseai.github.io/noise-tail

📄 PDF Abstract BibTeX arXiv:2309.14330

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoiser

2026-01-04 · Jiawei Fang, Ruonan Zheng, Xiaoxia Gao, Shifan Jiang 외 arxiv

Wearable inertial motion capture (MoCap) provides a portable, occlusion-free, and privacy-preserving alternative to camera-based systems, but its accuracy depends on tightly attached sensors - an intrusive and uncomforta…

Pose Prediction

UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks

2023-02-24 · Mahum Naseer, Bharath Srinivas Prabakaran, Osman Hasan, Muhammad Shafique

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can b…

Gaussian-smoothed Imbalance Data Improves Speech Emotion Recognition

2023-02-17 · Xuefeng Liang, Hexin Jiang, Wenxin Xu, Ying Zhou

In speech emotion recognition tasks, models learn emotional representations from datasets. We find the data distribution in the IEMOCAP dataset is very imbalanced, which may harm models to learn a better representation. …

Data AugmentationEmotion RecognitionSpeech Emotion Recognition

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

2024-08-21 · Minghao Liu, Zonglin Di, Jiaheng Wei, Zhongruo Wang 외

Large-scale data collection is essential for developing personalized training data, mitigating the shortage of training data, and fine-tuning specialized models. However, creating high-quality datasets quickly and accura…

Code Generationimage-classificationImage ClassificationLabel Error Detection

Combating Noisy Labels in Long-Tailed Image Classification

2022-09-01 · Chaowei Fang, Lechao Cheng, Huiyan Qi, Dingwen Zhang

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced…

Classificationimage-classificationImage Classification