Yukun Zhu
YOU?
Author Swipe
View article: Comprehensive assessment of erenumab efficacy in participants with high‐frequency episodic migraine with at least one previously failed preventive treatment: The <scp>EMBRACE</scp> study
Comprehensive assessment of erenumab efficacy in participants with high‐frequency episodic migraine with at least one previously failed preventive treatment: The <span>EMBRACE</span> study Open
Objective To evaluate the effect of erenumab treatment beyond monthly migraine days in patients with high‐frequency episodic migraine who did not respond to at least one previous migraine preventive treatment. Background Reduction in month…
View article: Recent Advances in Elemental Red Phosphorus‐Based Photocatalysts for Solar Driven Hydrogen Production
Recent Advances in Elemental Red Phosphorus‐Based Photocatalysts for Solar Driven Hydrogen Production Open
The development of efficient photocatalyst materials is crucial for solar hydrogen production through photocatalytic water splitting. Recently, earth‐abundant elemental red phosphorus (RP) materials with broader light absorption ability an…
View article: X-PRINT:Platform-Agnostic and Scalable Fine-Grained Encrypted Traffic Fingerprinting
X-PRINT:Platform-Agnostic and Scalable Fine-Grained Encrypted Traffic Fingerprinting Open
Although encryption protocols such as TLS are widely de-ployed,side-channel metadata in encrypted traffic still reveals patterns that allow application and behavior inference.How-ever,existing fine-grained fingerprinting approaches face tw…
View article: Red Blood Cell Membrane‐Camouflaged Red Phosphorus‐Modified C<sub>3</sub>N<sub>4</sub> for Enhanced Tumoral Photodynamic Therapy
Red Blood Cell Membrane‐Camouflaged Red Phosphorus‐Modified C<sub>3</sub>N<sub>4</sub> for Enhanced Tumoral Photodynamic Therapy Open
The clinical application of photodynamic therapy (PDT) faces limitations due to the poor tumor‐targeting efficiency and systemic toxicity of conventional photosensitizers. To overcome these challenges, a biomimetic nanoplatform (C3N4‐RP@RB…
View article: Association of low-density lipoprotein/high-density lipoprotein ratio with cognition, Alzheimer’s disease biomarkers and brain structure
Association of low-density lipoprotein/high-density lipoprotein ratio with cognition, Alzheimer’s disease biomarkers and brain structure Open
Background The relationship between the low-density lipoprotein/high-density lipoprotein (LDL/HDL) ratio, an indicator of lipid metabolism and assessment of cardiovascular disease (CVD) risk, and Alzheimer’s disease (AD) is unclear. Method…
View article: Analysis of the energy saving potential of natural ventilation of teaching buildings in colleges in hot summer and cold winter areas
Analysis of the energy saving potential of natural ventilation of teaching buildings in colleges in hot summer and cold winter areas Open
The building sector is a major contributor to energy consumption and carbon emissions. Efficiently reducing energy consumption and environmental pollution is crucial for sustainable social development. Natural ventilation, as a passive coo…
View article: Neptune: The Long Orbit to Benchmarking Long Video Understanding
Neptune: The Long Orbit to Benchmarking Long Video Understanding Open
We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and models are focused on short clips (10s-30s). While some long v…
View article: Enhanced Renal Carcinoma Treatment via Synergistic Photothermal/Photodynamic Therapy Using Hittorf's Phosphorus‐Decorated Polymeric Carbon Nitride Heterostructure
Enhanced Renal Carcinoma Treatment via Synergistic Photothermal/Photodynamic Therapy Using Hittorf's Phosphorus‐Decorated Polymeric Carbon Nitride Heterostructure Open
Nanostructured heterojunctions offer a promising solution to overcome the limitations of narrow absorption spectra, limited penetration depths, and potential harm to healthy cells in phototherapy for clear cell renal cell carcinoma (ccRCC)…
View article: Simulation Study on the Impact of Building Orientation Variation on Annual Energy Consumption in Hefei Area
Simulation Study on the Impact of Building Orientation Variation on Annual Energy Consumption in Hefei Area Open
Under the background of increasingly serious energy crisis, promoting the development of building energy conservation can effectively alleviate the problem of an energy shortage, ensure stable economic development, and energy-saving design…
View article: FeO @FeP heterostructure: Surface phosphorization toward efficient photocatalytic Fenton-like norfloxacin removal
FeO @FeP heterostructure: Surface phosphorization toward efficient photocatalytic Fenton-like norfloxacin removal Open
The residues of daily-used antibiotics are difficult to be removed and very harmful to the environment. Herein, FeOx@FeP heterostructure was constructed by surface phosphorization of hematite (α-Fe2O3) synthesized via a facile hydrothermal…
View article: Federated Multi-Target Domain Adaptation
Federated Multi-Target Domain Adaptation Open
Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision ta…
View article: DeepLab2: A TensorFlow Library for Deep Labeling
DeepLab2: A TensorFlow Library for Deep Labeling Open
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepL…
View article: Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze
Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze Open
Mutual gaze detection, i.e., predicting whether or not two people are looking at each other, plays an important role in understanding human interactions. In this work, we focus on the task of image-based mutual gaze detection, and propose …
View article: BasisNet: Two-stage Model Synthesis for Efficient Inference
BasisNet: Two-stage Model Synthesis for Efficient Inference Open
In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form. Our approach incorporates a lightweight model to preview t…
View article: Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data Open
This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign…
View article: STEP: Segmenting and Tracking Every Pixel
STEP: Segmenting and Tracking Every Pixel Open
The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation. Our work is the first that targets this task in a real-world setting requiring dense interpretation in both spatia…
View article: ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation Open
In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the point clouds from perspective image sequences while providi…
View article: MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers Open
We present MaX-DeepLab, the first end-to-end model for panoptic segmentation. Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks and hand-designed components, such as box detection, non-maximum suppres…
View article: Ranking Neural Checkpoints
Ranking Neural Checkpoints Open
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from vari…