Search Results for author: Hongyu Wang

Found 31 papers, 12 papers with code

Prompt-Guided Generation of Structured Chest X-Ray Report Using a Pre-trained LLM

no code implementations17 Apr 2024 Hongzhao Li, Hongyu Wang, Xia Sun, Hua He, Jun Feng

Our method introduces a prompt-guided approach to generate structured chest X-ray reports using a pre-trained large language model (LLM).

Anatomy Language Modelling +3

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

4 code implementations27 Feb 2024 Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, Furu Wei

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs).

DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM

no code implementations3 Jan 2024 Mingrui Li, Yiming Zhou, Guangan Jiang, Tianchen Deng, Yangyang Wang, Hongyu Wang

To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model.

Loop Closure Detection Optical Flow Estimation +1

Temporal Adaptive RGBT Tracking with Modality Prompt

no code implementations2 Jan 2024 Hongyu Wang, Xiaotao Liu, YiFan Li, Meng Sun, Dian Yuan, Jing Liu

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving.

Autonomous Driving Rgb-T Tracking

VOT: Revolutionizing Speaker Verification with Memory and Attention Mechanisms

no code implementations28 Dec 2023 Hongyu Wang, Hui Li, Bo Li

Speaker verification is to judge the similarity of two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small intra-speaker distances and large inter-speaker distances. We propose a novel model named Voice Transformer(VOT) for speaker verification.

Speaker Verification

BitNet: Scaling 1-bit Transformers for Large Language Models

2 code implementations17 Oct 2023 Hongyu Wang, Shuming Ma, Li Dong, Shaohan Huang, Huaijie Wang, Lingxiao Ma, Fan Yang, Ruiping Wang, Yi Wu, Furu Wei

The increasing size of large language models has posed challenges for deployment and raised concerns about environmental impact due to high energy consumption.

Language Modelling Quantization

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine

1 code implementation23 Aug 2023 Chenrui Zhang, Lin Liu, Jinpeng Wang, Chuyuan Wang, Xiao Sun, Hongyu Wang, Mingchen Cai

Moreover, to enhance stability of the prompt effect evaluation, we propose a novel prompt bagging method involving forward and backward thinking, which is superior to majority voting and is beneficial for both feedback and weight calculation in boosting.

Ensemble Learning Hallucination

Hyperspectral Target Detection Based on Low-Rank Background Subspace Learning and Graph Laplacian Regularization

no code implementations1 Jun 2023 Dunbin Shen, Xiaorui Ma, Wenfeng Kong, Jiacheng Tian, Hongyu Wang

Firstly, to obtain a complete and pure background dictionary, we propose a LRR-based background subspace learning method by jointly mining the low-dimensional structure of all pixels.

High-Accuracy Approximation of Evolutionary Pairwise Games on Complex Networks

no code implementations12 Jan 2023 Hongyu Wang, Aming Li, Long Wang

Previous studies have shown that the topological properties of a complex network, such as heterogeneity and average degree, affect the evolutionary game dynamics on it.

Vocal Bursts Intensity Prediction

Feature Extractor Stacking for Cross-domain Few-shot Learning

1 code implementation12 May 2022 Hongyu Wang, Eibe Frank, Bernhard Pfahringer, Michael Mayo, Geoffrey Holmes

Recently published CDFSL methods generally construct a universal model that combines knowledge of multiple source domains into one feature extractor.

cross-domain few-shot learning Image Classification

DeepNet: Scaling Transformers to 1,000 Layers

6 code implementations1 Mar 2022 Hongyu Wang, Shuming Ma, Li Dong, Shaohan Huang, Dongdong Zhang, Furu Wei

In this paper, we propose a simple yet effective method to stabilize extremely deep Transformers.


Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design

no code implementations25 Oct 2021 Wei Zhou, Xiangyu Zhang, Hongyu Wang, Shenghua Gao, Xin Lou

It is shown that by adding another transformation, the proposed method is able to synthesize high-quality RAW Bayer images with arbitrary size.

Demosaicking Image Generation +3

Deep Learning for Depression Recognition with Audiovisual Cues: A Review

no code implementations27 May 2021 Lang He, MingYue Niu, Prayag Tiwari, Pekka Marttinen, Rui Su, Jiewei Jiang, Chenguang Guo, Hongyu Wang, Songtao Ding, Zhongmin Wang, Wei Dang, Xiaoying Pan

Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection.

Depression Detection

Classification of Smoking and Calling using Deep Learning

1 code implementation15 Dec 2020 Miaowei Wang, Alexander William Mohacey, Hongyu Wang, James Apfel

Since 2014, very deep convolutional neural networks have been proposed and become the must-have weapon for champions in all kinds of competition.

Classification General Classification

Carleson measures on convex domains

no code implementations26 Nov 2020 Haichou Li, Jinsong Liu, Hongyu Wang

Following M. Abate and A. Saracco's work on strongly pseudoconvex domains in $\mathbb{C}^n$, we characterize Carleson measures of $A^2(D)$ in bounded convex domains with smooth boundary of finite type.

Complex Variables

AEGCN: An Autoencoder-Constrained Graph Convolutional Network

1 code implementation3 Jul 2020 Mingyuan Ma, Sen Na, Hongyu Wang

In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks.

Decoder Graph Attention +1

Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network

no code implementations26 Feb 2020 Hongyu Wang, Guangcun Shan

In this paper, a robust multiscale neural network is proposed to recognize handwritten mathematical expressions and output LaTeX sequences, which can effectively and correctly focus on where each step of output should be concerned and has a positive effect on analyzing the two-dimensional structure of handwritten mathematical expressions and identifying different mathematical symbols in a long expression.

Deep Multiphase Level Set for Scene Parsing

no code implementations8 Oct 2019 Pingping Zhang, Wei Liu, Yinjie Lei, Hongyu Wang, Huchuan Lu

The proposed method consists of three modules, i. e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning.

Image Segmentation Scene Parsing +1

Robust Encoder-Decoder Learning Framework towards Offline Handwritten Mathematical Expression Recognition Based on Multi-Scale Deep Neural Network

no code implementations8 Feb 2019 Guangcun Shan, Hongyu Wang, Wei Liang

Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition.


ChestNet: A Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography

no code implementations9 Jul 2018 Hongyu Wang, Yong Xia

Computer-aided techniques may lead to more accurate and more acces-sible diagnosis of thorax diseases on chest radiography.

General Classification Weakly-supervised Learning

Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps

no code implementations22 Feb 2018 Pingping Zhang, Wei Liu, Dong Wang, Yinjie Lei, Hongyu Wang, Chunhua Shen, Huchuan Lu

Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.

Object Object Tracking +2

Video Person Re-identification by Temporal Residual Learning

no code implementations22 Feb 2018 Ju Dai, Pingping Zhang, Huchuan Lu, Hongyu Wang

In this paper, we propose a novel feature learning framework for video person re-identification (re-ID).

Video-Based Person Re-Identification

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

1 code implementation ICCV 2017 Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, Xiang Ruan

In addition, to achieve accurate boundary inference and semantic enhancement, edge-aware feature maps in low-level layers and the predicted results of low resolution features are recursively embedded into the learning framework.

Ranked #20 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)

Object object-detection +2

End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks

no code implementations26 Jul 2016 Yifan Wang, Lijun Wang, Hongyu Wang, Peihua Li

In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN.

Image Super-Resolution

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