Search Results for author: Hang Yang

Found 30 papers, 11 papers with code

PTQ4RIS: Post-Training Quantization for Referring Image Segmentation

1 code implementation25 Sep 2024 Xiaoyan Jiang, Hang Yang, Kaiying Zhu, Xihe Qiu, Shibo Zhao, Sifan Zhou

Specifically, we first conduct an in-depth analysis of the root causes of performance degradation in RIS model quantization and propose dual-region quantization (DRQ) and reorder-based outlier-retained quantization (RORQ) to address the quantization difficulties in visual and text encoders.

Image Segmentation Quantization +2

Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis

1 code implementation4 Jan 2024 Jiahui Peng, Jing Gao, Xin Tong, Jing Guo, Hang Yang, Jianchuan Qi, Ruiqiao Li, Nan Li, Ming Xu

In the evolving field of corporate sustainability, analyzing unstructured Environmental, Social, and Governance (ESG) reports is a complex challenge due to their varied formats and intricate content.

Empowering Working Memory for Large Language Model Agents

no code implementations22 Dec 2023 Jing Guo, Nan Li, Jianchuan Qi, Hang Yang, Ruiqiao Li, Yuzhen Feng, Si Zhang, Ming Xu

The limitations of traditional LLM memory designs are analyzed, including their isolation of distinct dialog episodes and lack of persistent memory links.

Language Modelling Large Language Model +1

DKiS: Decay weight invertible image steganography with private key

1 code implementation30 Nov 2023 Hang Yang, Yitian Xu, Xuhua Liu

Image steganography, defined as the practice of concealing information within another image, traditionally encounters security challenges when its methods become publicly known or are under attack.

Image Steganography

PRIS: Practical robust invertible network for image steganography

1 code implementation24 Sep 2023 Hang Yang, Yitian Xu, Xuhua Liu, Xiaodong Ma

Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion.

Image Steganography

Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation

1 code implementation29 Jun 2023 Hanqiu Chen, Hang Yang, Stephen Fitzmeyer, Cong Hao

This paper introduces Rapid-INR, a novel approach that utilizes INR for encoding and compressing images, thereby accelerating neural network training in computer vision tasks.

Image Classification Image Compression +1

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

1 code implementation13 Jul 2022 Haoyu Wang, Nan Wu, Hang Yang, Cong Hao, Pan Li

Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled.

Combinatorial Optimization

Fast and accurate waveform modeling of long-haul multi-channel optical fiber transmission using a hybrid model-data driven scheme

no code implementations12 Jan 2022 Hang Yang, Zekun Niu, Haochen Zhao, Shilin Xiao, Weisheng Hu, Lilin Yi

The modeling of optical wave propagation in optical fiber is a task of fast and accurate solving the nonlinear Schr\"odinger equation (NLSE), and can enable the optical system design, digital signal processing verification and fast waveform calculation.

TE-YOLOF: Tiny and efficient YOLOF for blood cell detection

no code implementations27 Aug 2021 Fanxin Xu, Xiangkui Li, Hang Yang, Yali Wang, Wei Xiang

In this work, an object detector based on YOLOF has been proposed to detect blood cell objects such as red blood cells, white blood cells and platelets.

Blood Cell Detection Cell Detection +1

Document-level Event Extraction via Parallel Prediction Networks

2 code implementations ACL 2021 Hang Yang, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Taifeng Wang

We argue that sentence-level extractors are ill-suited to the DEE task where event arguments always scatter across sentences and multiple events may co-exist in a document.

Decoder Document-level Event Extraction +2

DPN-SENet:A self-attention mechanism neural network for detection and diagnosis of COVID-19 from chest x-ray images

1 code implementation20 May 2021 Bo Cheng, Ruhui Xue, Hang Yang, Laili Zhu, Wei Xiang

We propose a deep learning model that can help radiologists and clinicians use chest X-rays to diagnose COVID-19 cases and show the diagnostic features of pneumonia.

Data Augmentation

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

1 code implementation ICCV 2021 Le Hui, Hang Yang, Mingmei Cheng, Jin Xie, Jian Yang

In order to obtain discriminative global descriptors, we construct a pyramid VLAD module to aggregate the multi-scale feature maps of point clouds into the global descriptors.

3D Place Recognition Point Cloud Retrieval +1

Peer-to-Peer Localization for Single-Antenna Devices

no code implementations10 Dec 2020 Xianan Zhang, Wei Wang, Xuedou Xiao, Hang Yang, Xinyu Zhang, Tao Jiang

In this paper, we present P2PLocate, a peer-to-peer localization system that enables a single-antenna device co-located with a batteryless backscatter tag to localize another single-antenna device with decimeter-level accuracy.

Indoor Localization TAG

Channel-wise Alignment for Adaptive Object Detection

no code implementations7 Sep 2020 Hang Yang, Shan Jiang, Xinge Zhu, Mingyang Huang, Zhiqiang Shen, Chunxiao Liu, Jianping Shi

Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest, which naturally, cannot fully utilize the fine-grained channel information.

Instance Segmentation Object +3

Select Good Regions for Deblurring based on Convolutional Neural Networks

no code implementations12 Aug 2020 Hang Yang, Xiaotian Wu, Xinglong Sun

The goal of blind image deblurring is to recover sharp image from one input blurred image with an unknown blur kernel.

Blind Image Deblurring Image Deblurring

Fast and Accurate Optical Fiber Channel Modeling Using Generative Adversarial Network

no code implementations28 Feb 2020 Hang Yang, Zekun Niu, Shilin Xiao, Jiafei Fang, Zhiyang Liu, David Faninsin, Lilin Yi

In this work, a new data-driven fiber channel modeling method, generative adversarial network (GAN) is investigated to learn the distribution of fiber channel transfer function.

Generative Adversarial Network

Population pharmacokinetics and dosing regimen optimization of tacrolimus in Chinese lung transplant recipients

no code implementations1 Feb 2020 Xiaojun Cai, Huizhu Song, Zheng Jiao, Hang Yang, Min Zhu, Chengyu Wang, Dong Wei, Lingzhi Shi, Bo Wu, Jinyu Chen

Given the nonlinear kinetics of tacrolimus and large variability, population pharmacokinetic model should be combined with therapeutic drug monitoring to optimize individualized therapy.

Depth Image Upsampling based on Guided Filter with Low Gradient Minimization

no code implementations12 Nov 2018 Hang Yang, Zhongbo Zhang

In our framework, the upscaling of a low-resolution depth image is guided by a corresponding intensity images, we formulate it as a cost aggregation problem with the guided filter.

Depth Image Upsampling

A Robust Local Binary Similarity Pattern for Foreground Object Detection

no code implementations16 Oct 2018 Dongdong Zeng, Ming Zhu, Hang Yang

First, we propose a robust texture operator named Robust Local Binary Similarity Pattern (RLBSP), which shows strong robustness to illumination variations and dynamic backgrounds.

Object object-detection +2

Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms

1 code implementation EMNLP 2018 Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, Yantao Jia

Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information.

Event Detection Sentence

Guided Filter based Edge-preserving Image Non-blind Deconvolution

no code implementations7 Sep 2016 Hang Yang, Ming Zhu, Zhongbo Zhang, He-Yan Huang

In the denoising step, the guided filter is used with the two obtained images for efficient edge-preserving filtering.

Deblurring Denoising +1

An Adaptive Parameter Estimation for Guided Filter based Image Deconvolution

no code implementations6 Sep 2016 Hang Yang, Zhongbo Zhang, Yujing Guan

Image deconvolution is still to be a challenging ill-posed problem for recovering a clear image from a given blurry image, when the point spread function is known.

Deblurring Denoising +2

Structured Indoor Modeling

no code implementations ICCV 2015 Satoshi Ikehata, Hang Yang, Yasutaka Furukawa

The grammar then drives a principled new reconstruction algorithm, where the grammar rules are sequentially applied to recover a structured model.

Dual Domain Filters Based Texture and Structure Preserving Image Non-Blind Deconvolution

no code implementations CVPR 2015 Hang Yang, Ming Zhu, Yan Niu, Yujing Guan, Zhongbo Zhang

Image deconvolution continues to be an active research topic of recovering a sharp image, given a blurry one generated by a convolution.

Deblurring Image Deconvolution

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