Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

Ohkawa, Takehiko; Li, Yu-Jhe; Fu, Qichen; Furuta, Ryosuke; Sato, Yoichi

doi:10.1007/978-3-031-20077-9_5

Cited by 13 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their proposed approach integrates the confidence estimation method into self-training via mutual training, employing knowledge distillation with a student network and two teacher networks. They demonstrated superior performance over existing methods across various imaging conditions and enhanced qualitative results in in-the-wild, egocentric videos [34].…”

Section: Machine Learningmentioning

confidence: 92%

Machine Learning-Based Hand Pose Generation Using a Haptic Controller

Choi,

Lee,

et al. 2024

Electronics

View full text Add to dashboard Cite

In this study, we present a novel approach to derive hand poses from data input via a haptic controller, leveraging machine learning techniques. The input values received from the haptic controller correspond to the movement of five fingers, each assigned a value between 0.0 and 1.0 based on the applied pressure. The wide array of possible finger movements requires a substantial amount of motion capture data, making manual data integration difficult. This challenge is primary due to the need to process and incorporate large volumes of diverse movement information. To tackle this challenge, our proposed method automates the process by utilizing machine learning algorithms to convert haptic controller inputs into hand poses. This involves training a machine learning model using supervised learning, where hand poses are matched with their corresponding input values, and subsequently utilizing this trained model to generate hand poses in response to user input. In our experiments, we assessed the accuracy of the generated hand poses by analyzing the angles and positions of finger joints. As the quantity of training data increased, the margin of error decreased, resulting in generated poses that closely emulated real-world hand movements.

show abstract

Section: Machine Learningmentioning

confidence: 92%

Machine Learning-Based Hand Pose Generation Using a Haptic Controller

Choi,

Lee,

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Other instance weighting methods in the shallow regime, [14,74,75] have been explored for a different range of applications. Some specific vision applications have been explored in the context of UDA [31,34,36,50] , such as monocular depth estimation [1,5,43,63] or gaze estimation [4,26]. However, these methods aim at improving upon a specific task and not for regression tasks in general.…”

Section: Related Workmentioning

confidence: 99%

DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices

Nejjar¹,

Wang²,

Fink³

2023

Preprint

View full text Add to dashboard Cite

Unsupervised Domain Adaptation Regression (DAR) aims to bridge the domain gap between a labeled source dataset and an unlabelled target dataset for regression problems. Recent works mostly focus on learning a deep feature encoder by minimizing the discrepancy between source and target features. In this work, we present a different perspective for the DAR problem by analyzing the closed-form ordinary least square (OLS) solution to the linear regressor in the deep domain adaptation context. Rather than aligning the original feature embedding space, we propose to align the inverse Gram matrix of the features, which is motivated by its presence in the OLS solution and the Gram matrix's ability to capture the feature correlations. Specifically, we propose a simple yet effective DAR method which leverages the pseudo-inverse lowrank property to align the scale and angle in a selected subspace generated by the pseudo-inverse Gram matrix of the two domains. We evaluate our method on three domain adaptation regression benchmarks. Experimental results demonstrate that our method achieves state-of-the-art performance. Our code is available at https://github. com/ismailnejjar/DARE-GRAM .

show abstract