Stella X. Yu
YOU?
Author Swipe
View article: Design, Performance Testing, and Experimental Validation of Modular Soft Robots Based on Thin-Film Actuators
Design, Performance Testing, and Experimental Validation of Modular Soft Robots Based on Thin-Film Actuators Open
Currently, soft robots face challenges such as low motion efficiency, susceptibility to damage in traditional silicone materials, and difficulty in achieving reproducible manufacturing. To address these issues, we integrate flexible film m…
View article: Design, Performance Testing, and Experimental Validation of Modular Soft Robots Based on Thin‐Film Actuators
Design, Performance Testing, and Experimental Validation of Modular Soft Robots Based on Thin‐Film Actuators Open
Currently, soft robots face challenges such as low motion efficiency, susceptibility to damage in traditional silicone materials, and difficulty in achieving reproducible manufacturing. To address these issues, we integrate flexible film m…
View article: Test-Time Canonicalization by Foundation Models for Robust Perception
Test-Time Canonicalization by Foundation Models for Robust Perception Open
Perception in the real world requires robustness to diverse viewing conditions. Existing approaches often rely on specialized architectures or training with predefined data augmentations, limiting adaptability. Taking inspiration from ment…
View article: Neutrophil-derived LL37 mediates IgA nephropathy via NETs-dependent mechanism
Neutrophil-derived LL37 mediates IgA nephropathy via NETs-dependent mechanism Open
IgAN is a common cause leading to end-stage renal disease. The deposition of pathogenic IgA in the glomerular mesangium is a critical step. However, the mechanisms of pathogenic IgA crossing the glomerular filtration barrier remain unclear…
View article: Normalize Filters! Classical Wisdom for Deep Vision
Normalize Filters! Classical Wisdom for Deep Vision Open
Classical image filters, such as those for averaging or differencing, are carefully normalized to ensure consistency, interpretability, and to avoid artifacts like intensity shifts, halos, or ringing. In contrast, convolutional filters lea…
View article: Designing ecological buffer zones for sustainable agriculture: A case study of Fuxian Lake
Designing ecological buffer zones for sustainable agriculture: A case study of Fuxian Lake Open
View article: Let Humanoids Hike! Integrative Skill Development on Complex Trails
Let Humanoids Hike! Integrative Skill Development on Complex Trails Open
Hiking on complex trails demands balance, agility, and adaptive decision-making over unpredictable terrain. Current humanoid research remains fragmented and inadequate for hiking: locomotion focuses on motor skills without long-term goals …
View article: Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes
Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes Open
The purpose of this study is to examine and interpret machine learning models that predict dry eye (DE)-related clinical signs, subjective symptoms, and clinician diagnoses by heavily weighting lifestyle factors in the predictions. Machine…
View article: The Predominant Role of Stochastic Processes in Bacterial Community Assembly across Varied Hydrological Connectivity of Watershed Surface Water
The Predominant Role of Stochastic Processes in Bacterial Community Assembly across Varied Hydrological Connectivity of Watershed Surface Water Open
View article: Author Correction: Coordinate-based neural representations for computational adaptive optics in widefield microscopy
Author Correction: Coordinate-based neural representations for computational adaptive optics in widefield microscopy Open
View article: ANKRD5: a key component of the axoneme required for sperm motility and male fertility
ANKRD5: a key component of the axoneme required for sperm motility and male fertility Open
Sperm motility is essential for male fertility and depends on the structural integrity of the sperm axoneme, which features a canonical "9+2" microtubule arrangement. This structure comprises nine outer doublet microtubules (DMTs) that are…
View article: Adaptive optical correction for<i>in vivo</i>two-photon fluorescence microscopy with neural fields
Adaptive optical correction for<i>in vivo</i>two-photon fluorescence microscopy with neural fields Open
Adaptive optics (AO) restore ideal imaging performance in complex samples by measuring and correcting optical aberrations, but often require custom-built microscopes with carefully aligned wavefront sensing/shaping devices and can be susce…
View article: BEAT: Berkeley Emotion and Affect Tracking Dataset
BEAT: Berkeley Emotion and Affect Tracking Dataset Open
View article: A machine learning approach to predicting dry eye-related signs, symptoms and diagnoses from meibography images
A machine learning approach to predicting dry eye-related signs, symptoms and diagnoses from meibography images Open
View article: Artificial Intelligence Models Utilize Lifestyle Factors to Predict Dry Eye-Related Outcomes
Artificial Intelligence Models Utilize Lifestyle Factors to Predict Dry Eye-Related Outcomes Open
Purpose To examine and interpret machine learning models that predict dry eye (DE)-related clinical signs, subjective symptoms, and clinician diagnoses by heavily weighting lifestyle factors in the predictions. Methods Machine learning mod…
View article: Enhancing Meibography Image Analysis Through Artificial Intelligence–Driven Quantification and Standardization for Dry Eye Research
Enhancing Meibography Image Analysis Through Artificial Intelligence–Driven Quantification and Standardization for Dry Eye Research Open
The study presents a standardized method for meibography image analysis. This method could serve as a valuable tool in facilitating more targeted investigations into MG characteristics.
View article: Visually Consistent Hierarchical Image Classification
Visually Consistent Hierarchical Image Classification Open
Hierarchical classification predicts labels across multiple levels of a taxonomy, e.g., from coarse-level 'Bird' to mid-level 'Hummingbird' to fine-level 'Green hermit', allowing flexible recognition under varying visual conditions. It is …
View article: Changes in nutritional status and the development of obesity and metabolic syndrome following pediatric heart transplantation
Changes in nutritional status and the development of obesity and metabolic syndrome following pediatric heart transplantation Open
Background Nutritional status in pediatric patients undergoing heart transplantation (HT) is frequently a focus of clinical management and requires high resource utilization. Pre‐operative nutrition status has been shown to affect post‐ope…
View article: Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys
Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys Open
Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification …
View article: Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization
Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization Open
Learning visual features from unlabeled images has proven successful for semantic categorization, often by mapping different $views$ of the same object to the same feature to achieve recognition invariance. However, visual recognition invo…
View article: A Machine Learning Approach to Predicting Dry Eye-Related Signs, Symptoms and Diagnoses from Meibography Images
A Machine Learning Approach to Predicting Dry Eye-Related Signs, Symptoms and Diagnoses from Meibography Images Open
View article: Debiased Learning for Remote Sensing Data
Debiased Learning for Remote Sensing Data Open
Deep learning has had remarkable success at analyzing handheld imagery such as consumer photos due to the availability of large-scale human annotations (e.g., ImageNet). However, remote sensing data lacks such extensive annotation and thus…
View article: Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models
Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models Open
Existing building recognition methods, exemplified by BRAILS, utilize supervised learning to extract information from satellite and street-view images for classification and segmentation. However, each task module requires human-annotated …
View article: How to guess a gradient
How to guess a gradient Open
How much can you say about the gradient of a neural network without computing a loss or knowing the label? This may sound like a strange question: surely the answer is "very little." However, in this paper, we show that gradients are more …
View article: Learning to Transform for Generalizable Instance-wise Invariance
Learning to Transform for Generalizable Instance-wise Invariance Open
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too m…
View article: VEATIC: Video-based Emotion and Affect Tracking in Context Dataset
VEATIC: Video-based Emotion and Affect Tracking in Context Dataset Open
Human affect recognition has been a significant topic in psychophysics and computer vision. However, the currently published datasets have many limitations. For example, most datasets contain frames that contain only information about faci…
View article: Editor’s Note: Special Issue from Winter Conference on Applications of Computer Vision - WACV 2023
Editor’s Note: Special Issue from Winter Conference on Applications of Computer Vision - WACV 2023 Open
View article: An Enhanced Dataset for Inferential Emotion Tracking in Humans and Machines
An Enhanced Dataset for Inferential Emotion Tracking in Humans and Machines Open
Emotion perception is fundamental to human experience, and it reveals both the sophistication and richness of vision. Although emotion perception depends in part on face processing, it also hinges critically on background scene context (e.…
View article: Serial Dependence Biases Realistic Skin Cancer Diagnosis
Serial Dependence Biases Realistic Skin Cancer Diagnosis Open
Serial Dependence is a perceptual phenomenon in which the visual system tends to bias representations toward recent visual history (Fischer & Whitney, 2014; Cicchini, et al., 2014). Studies under both lab and naturalistic scenarios have sh…
View article: Coordinate-based neural representations for computational adaptive optics in widefield microscopy
Coordinate-based neural representations for computational adaptive optics in widefield microscopy Open
Widefield microscopy is widely used for non-invasive imaging of biological structures at subcellular resolution. When applied to complex specimen, its image quality is degraded by sample-induced optical aberration. Adaptive optics can corr…