Search Results for author: Yong Huang

Found 20 papers, 3 papers with code

ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition

1 code implementation23 Feb 2024 Lu Ye, Ze Tao, Yong Huang, Yang Li

In this paper, we introduce ChunkAttention, a prefix-aware self-attention module that can detect matching prompt prefixes across multiple requests and share their key/value tensors in memory at runtime to improve the memory utilization of KV cache.

MolNexTR: A Generalized Deep Learning Model for Molecular Image Recognition

1 code implementation6 Mar 2024 Yufan Chen, Ching Ting Leung, Yong Huang, Jianwei Sun, Hao Chen, Hanyu Gao

In addition, it employs a series of novel augmentation algorithms to significantly enhance the robustness and performance of the model.

Data Augmentation

Explored An Effective Methodology for Fine-Grained Snake Recognition

1 code implementation24 Jul 2022 Yong Huang, Aderon Huang, Wei Zhu, Yanming Fang, Jinghua Feng

Then, in order to take full advantage of unlabeled datasets, we use self-supervised learning and supervised learning joint training to provide pre-trained model.

Fine-Grained Image Classification Self-Supervised Learning

Greedy Graph Searching for Vascular Tracking in Angiographic Image Sequences

no code implementations25 May 2018 Huihui Fang, Jian Yang, Jianjun Zhu, Danni Ai, Yong Huang, Yurong Jiang, Hong Song, Yongtian Wang

The vascular branch was described using a vascular centerline extraction method with multi-probability fusion-based topology optimization.

Dynamic Time Warping Image Registration

Bayesian System Identification based on Hierarchical Sparse Bayesian Learning and Gibbs Sampling with Application to Structural Damage Assessment

no code implementations13 Jan 2017 Yong Huang, James L. Beck, Hui Li

The focus in this paper is Bayesian system identification based on noisy incomplete modal data where we can impose spatially-sparse stiffness changes when updating a structural model.

Bayesian Inference

Hierarchical sparse Bayesian learning: theory and application for inferring structural damage from incomplete modal data

no code implementations21 Mar 2015 Yong Huang, James L. Beck

In this paper, we improve the theory of our previously proposed sparse Bayesian learning approach by eliminating an approximation and, more importantly, incorporating a constraint on stiffness increases.

Learning Theory

Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction

no code implementations8 Jul 2019 Fangqiao Hu, Jin Zhao, Yong Huang, Hui Li

Considering the prior human knowledge that these structures are in conformity to regular spatial layouts in terms of components, a learning-based topology-aware 3D reconstruction method which can obtain high-level structural graph layouts and low-level 3D shapes from images is proposed in this paper.

3D Reconstruction Generating 3D Point Clouds

Recovering compressed images for automatic crack segmentation using generative models

no code implementations6 Mar 2020 Yong Huang, Haoyu Zhang, Hui Li, Stephen Wu

We develop a recovery framework for automatic crack segmentation of compressed crack images based on this new CS method and demonstrate the remarkable performance of the method taking advantage of the strong capability of generative models to capture the necessary features required in the crack segmentation task even the backgrounds of the generated images are not well reconstructed.

Compressive Sensing Crack Segmentation +1

A Multi-Modal and Multitask Benchmark in the Clinical Domain

no code implementations1 Jan 2021 Yong Huang, Edgar Mariano Marroquin, Volodymyr Kuleshov

Here, we introduce Multi-Modal Multitask MIMIC-III (M3) — a dataset and benchmark for evaluating machine learning algorithms in the healthcare domain.

BIG-bench Machine Learning Decompensation +2

Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos

no code implementations4 Jan 2021 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.

Time Series Analysis Video Forensics Cryptography and Security

LNSMM: Eye Gaze Estimation With Local Network Share Multiview Multitask

no code implementations18 Jan 2021 Yong Huang, Ben Chen, Daiming Qu

Eye gaze estimation has become increasingly significant in computer vision. In this paper, we systematically study the mainstream of eye gaze estimation methods, propose a novel methodology to estimate eye gaze points and eye gaze directions simultaneously. First, we construct a local sharing network for feature extraction of gaze points and gaze directions estimation, which can reduce network computational parameters and converge quickly;Second, we propose a Multiview Multitask Learning (MTL) framework, for gaze directions, a coplanar constraint is proposed for the left and right eyes, for gaze points, three views data input indirectly introduces eye position information, a cross-view pooling module is designed, propose joint loss which handle both gaze points and gaze directions estimation. Eventually, we collect a dataset to use of gaze points, which have three views to exist public dataset. The experiment show our method is state-of-the-art the current mainstream methods on two indicators of gaze points and gaze directions.

Gaze Estimation

ResAtom System: Protein and Ligand Affinity Prediction Model Based on Deep Learning

no code implementations17 Apr 2021 Yeji Wang, Shuo Wu, Yanwen Duan, Yong Huang

At the same time, we evaluated the performance of a variety of existing scoring functions in combination with ResAtom-Score in the absence of experimentally-determined conformations.

Molecular Docking Protein-Ligand Affinity Prediction

A Point Cloud-Based Deep Learning Strategy for Protein-Ligand Binding Affinity Prediction

no code implementations9 Jul 2021 Yeji Wang, Shuo Wu, Yanwen Duan, Yong Huang

These results suggest that point clouds derived from the PDBbind datasets are useful to evaluate the performance of 3D point clouds-centered deep learning algorithms, which could learn critical protein-ligand interactions from natural evolution or medicinal chemistry and have wide applications in studying protein-ligand interactions.

Drug Discovery Protein-Ligand Affinity Prediction

Forgery Attack Detection in Surveillance Video Streams Using Wi-Fi Channel State Information

no code implementations24 Jan 2022 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

The cybersecurity breaches expose surveillance video streams to forgery attacks, under which authentic streams are falsified to hide unauthorized activities.

Time Series Time Series Analysis +1

Parallel Fourier Ptychography reconstruction

no code implementations4 Mar 2022 Guocheng Zhou, Shaohui Zhang, Yao Hu, Lei Cao, Yong Huang, Qun Hao

Fourier ptychography has attracted a wide range of focus for its ability of large space-bandwidth-produce, and quantative phase measurement.

AI vs. Human -- Differentiation Analysis of Scientific Content Generation

no code implementations24 Jan 2023 Yongqiang Ma, Jiawei Liu, Fan Yi, Qikai Cheng, Yong Huang, Wei Lu, Xiaozhong Liu

We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text.

Text Detection

Low-Resource Multi-Granularity Academic Function Recognition Based on Multiple Prompt Knowledge

no code implementations5 May 2023 Jiawei Liu, Zi Xiong, Yi Jiang, Yongqiang Ma, Wei Lu, Yong Huang, Qikai Cheng

Inspired by recent advancement in prompt learning, in this paper, we propose the Mix Prompt Tuning (MPT), which is a semi-supervised method to alleviate the dependence on annotated data and improve the performance of multi-granularity academic function recognition tasks with a small number of labeled examples.

Sentence

Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method

no code implementations16 Feb 2024 Yong Huang, Charles A. Downs, Amir M. Rahmani

Warfarin, an anticoagulant medication, is formulated to prevent and address conditions associated with abnormal blood clotting, making it one of the most prescribed drugs globally.

Decision Making

Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense

no code implementations29 Feb 2024 Qiao Han, Yong Huang, xinling Guo, Yiteng Zhai, Yu Qin, Yao Yang

Recent studies have revealed the vulnerability of Deep Neural Networks (DNNs) to adversarial examples, which can easily fool DNNs into making incorrect predictions.

Adversarial Defense Adversarial Robustness +1

Cannot find the paper you are looking for? You can Submit a new open access paper.