Search Results for author: Fei Ma

Found 43 papers, 9 papers with code

Frequency-aware Event Cloud Network

no code implementations30 Dec 2024 Hongwei Ren, Fei Ma, Xiaopeng Lin, Yuetong Fang, Hongxiang Huang, Yulong Huang, Yue Zhou, Haotian Fu, ZiYi Yang, Fei Richard Yu, Bojun Cheng

Event cameras are biologically inspired sensors that emit events asynchronously with remarkable temporal resolution, garnering significant attention from both industry and academia.

Action Recognition Pose Estimation

Image Augmentation Agent for Weakly Supervised Semantic Segmentation

no code implementations29 Dec 2024 Wangyu Wu, Xianglin Qiu, Siqi Song, Zhenhong Chen, Xiaowei Huang, Fei Ma, Jimin Xiao

Therefore in this paper, we introduce a novel approach called Image Augmentation Agent (IAA) which shows that it is possible to enhance WSSS from data generation perspective.

Image Augmentation Weakly supervised Semantic Segmentation +1

Prompt Categories Cluster for Weakly Supervised Semantic Segmentation

no code implementations18 Dec 2024 Wangyu Wu, Xianglin Qiu, Siqi Song, Xiaowei Huang, Fei Ma, Jimin Xiao

Weakly Supervised Semantic Segmentation (WSSS), which leverages image-level labels, has garnered significant attention due to its cost-effectiveness.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis

no code implementations11 Dec 2024 Yifan Xie, Tao Feng, Xin Zhang, Xiangyang Luo, Zixuan Guo, Weijiang Yu, Heng Chang, Fei Ma, Fei Richard Yu

Furthermore, we integrate the audio-point enhancement module, which not only ensures the synchronization of the audio signal with the corresponding lip point cloud within the feature space, but also facilitates a deeper understanding of the interrelations among cross-modal conditional features.

A Review of Human Emotion Synthesis Based on Generative Technology

no code implementations10 Dec 2024 Fei Ma, Yukan Li, Yifan Xie, Ying He, Yi Zhang, Hongwei Ren, Zhou Liu, Wei Yao, Fuji Ren, Fei Richard Yu, Shiguang Ni

Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used.

CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis

no code implementations19 Nov 2024 Yifan Xie, Jingge Wang, Tao Feng, Fei Ma, Yang Li

Our method offers precise control over both the spatial attributes (polyp location and shape) and clinical characteristics of polyps that align with clinical descriptions.

Image Generation

PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting

no code implementations3 Nov 2024 Yanlong Wang, Jian Xu, Fei Ma, Shao-Lun Huang, Danny Dongning Sun, Xiao-Ping Zhang

Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies.

Time Series Time Series Forecasting

Cloud Adversarial Example Generation for Remote Sensing Image Classification

no code implementations21 Sep 2024 Fei Ma, Yuqiang Feng, Fan Zhang, Yongsheng Zhou

Common Perlin noise based cloud generation is a random, non-optimizable process, which cannot be directly used to attack the target models.

Adversarial Attack Adversarial Defense +2

SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing

no code implementations5 Sep 2024 Lingyu Xiong, Xize Cheng, Jintao Tan, Xianjia Wu, Xiandong Li, Lei Zhu, Fei Ma, Minglei Li, Huang Xu, Zhihu Hu

Ultimately, we inject the previously generated talking segmentation and style codes into a mask-guided StyleGAN to synthesize video frame.

Facial Editing Segmentation +1

GaussianPU: A Hybrid 2D-3D Upsampling Framework for Enhancing Color Point Clouds via 3D Gaussian Splatting

no code implementations3 Sep 2024 Zixuan Guo, Yifan Xie, Weijing Xie, Peng Huang, Fei Ma, Fei Richard Yu

Extensive experimental results on generating million-level point cloud data validate the effectiveness of our method, substantially improving the quality of colored point clouds and demonstrating significant potential for applications involving large-scale point clouds in autonomous robotics and human-robot interaction scenarios.

3DGS Image Restoration +3

Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression

1 code implementation28 Aug 2024 Haowen Hou, Fei Ma, Binwen Bai, Xinxin Zhu, Fei Yu

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks.

Learn To Learn More Precisely

no code implementations8 Aug 2024 Runxi Cheng, Yongxian Wei, Xianglong He, Wanyun Zhu, Songsong Huang, Fei Richard Yu, Fei Ma, Chun Yuan

Then in the outer loop, MSD utilizes the same query data to optimize the consistency of learned knowledge, enhancing the model's ability to learn more precisely.

Few-Shot Learning

Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation

no code implementations15 Jul 2024 Wangyu Wu, Tianhong Dai, Zhenhong Chen, Xiaowei Huang, Jimin Xiao, Fei Ma, Renrong Ouyang

Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness.

Contrastive Learning Weakly supervised Semantic Segmentation +1

Generative Technology for Human Emotion Recognition: A Scope Review

no code implementations4 Jul 2024 Fei Ma, Yucheng Yuan, Yifan Xie, Hongwei Ren, Ivan Liu, Ying He, Fuji Ren, Fei Richard Yu, Shiguang Ni

Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems.

Data Augmentation Emotional Intelligence +5

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

1 code implementation19 Jun 2024 Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models.

Language Modeling Language Modelling

Monaural speech enhancement on drone via Adapter based transfer learning

no code implementations16 May 2024 Xingyu Chen, Hanwen Bi, Wei-Ting Lai, Fei Ma

Monaural Speech enhancement on drones is challenging because the ego-noise from the rotating motors and propellers leads to extremely low signal-to-noise ratios at onboard microphones.

Speech Enhancement Transfer Learning

Variable Substitution and Bilinear Programming for Aligning Partially Overlapping Point Sets

no code implementations14 May 2024 Wei Lian, Zhesen Cui, Fei Ma, Hang Pan, WangMeng Zuo

In many applications, the demand arises for algorithms capable of aligning partially overlapping point sets while remaining invariant to the corresponding transformations.

Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba

no code implementations9 May 2024 Hongwei Ren, Yue Zhou, Jiadong Zhu, Haotian Fu, Yulong Huang, Xiaopeng Lin, Yuetong Fang, Fei Ma, Hao Yu, Bojun Cheng

However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties.

Mamba Temporal Information Extraction

A circular microphone array with virtual microphones based on acoustics-informed neural networks

1 code implementation24 Feb 2024 Sipei Zhao, Fei Ma

Acoustic beamforming aims to focus acoustic signals to a specific direction and suppress undesirable interferences from other directions.

Sound Field Reconstruction Using a Compact Acoustics-informed Neural Network

1 code implementation14 Feb 2024 Fei Ma, Sipei Zhao, Ian S. Burnett

Sound field reconstruction (SFR) augments the information of a sound field captured by a microphone array.

valid

Integrated Drill Boom Hole-Seeking Control via Reinforcement Learning

no code implementations4 Dec 2023 Haoqi Yan, Haoyuan Xu, Hongbo Gao, Fei Ma, Shengbo Eben Li, Jingliang Duan

To tackle these challenges, this study proposes an integrated drill boom control method based on Reinforcement Learning (RL).

reinforcement-learning Reinforcement Learning +1

Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation

no code implementations15 Oct 2023 Wangyu Wu, Tianhong Dai, Xiaowei Huang, Fei Ma, Jimin Xiao

In this paper, we introduce a novel ViT-based WSSS method named top-K pooling with patch contrastive learning (TKP-PCL), which employs a top-K pooling layer to alleviate the limitations of previous max pooling selection.

Contrastive Learning Weakly supervised Semantic Segmentation +1

Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation

no code implementations15 Oct 2023 Wangyu Wu, Tianhong Dai, Xiaowei Huang, Fei Ma, Jimin Xiao

Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels.

Image Augmentation Segmentation +2

An Active Noise Control System Based on Soundfield Interpolation Using a Physics-informed Neural Network

1 code implementation19 Sep 2023 Yile, Zhang, Fei Ma, Thushara Abhayapala, Prasanga Samarasinghe, Amy Bastine

An ANC system is designed to take advantage of the interpolated signal to reduce noise signal within the ROI.

Head-Related Transfer Function Interpolation with a Spherical CNN

1 code implementation15 Sep 2023 Xingyu Chen, Fei Ma, Yile Zhang, Amy Bastine, Prasanga N. Samarasinghe

The proposed method realizes the convolution process by decomposing and reconstructing HRTF through the Spherical Harmonics (SHs).

Use neural networks to recognize students' handwritten letters and incorrect symbols

no code implementations12 Sep 2023 Jiajun Zhu, Zichuan Yang, Binjie Hong, Jiacheng Song, Jiwei Wang, Tianhao Chen, Shuilan Yang, Zixun Lan, Fei Ma

Correcting students' multiple-choice answers is a repetitive and mechanical task that can be considered an image multi-classification task.

Multiple-choice

Circumvent spherical Bessel function nulls for open sphere microphone arrays with physics informed neural network

no code implementations1 Aug 2023 Fei Ma, Thushara D. Abhayapala, Prasanga N. Samarasinghe

A PINN models the measurement of an OSMA and predicts the sound field on another sphere whose radius is different from that of the OSMA.

Spatial Upsampling of Head-Related Transfer Functions Using a Physics-Informed Neural Network

1 code implementation27 Jul 2023 Fei Ma, Thushara D. Abhayapala, Prasanga N. Samarasinghe, Xingyu Chen

Head-related transfer function (HRTF) capture the information that a person uses to localize sound sources in space, and thus is crucial for creating personalized virtual acoustic experiences.

valid

Sound Field Estimation around a Rigid Sphere with Physics-informed Neural Network

1 code implementation26 Jul 2023 Xingyu Chen, Fei Ma, Amy Bastine, Prasanga Samarasinghe, Huiyuan Sun

To overcome this challenge, this paper proposes a method for sound field estimation based on a physics-informed neural network.

RCsearcher: Reaction Center Identification in Retrosynthesis via Deep Q-Learning

no code implementations28 Jan 2023 Zixun Lan, Zuo Zeng, Binjie Hong, Zhenfu Liu, Fei Ma

The critical insight in this framework is that the single or multiple reaction center must be a node-induced subgraph of the molecular product graph.

Deep Reinforcement Learning Graph Neural Network +2

Jet tagging algorithm of graph network with HaarPooling message passing

no code implementations25 Oct 2022 Fei Ma, Feiyi Liu, Wei Li

In this paper, we introduce an approach of GNNs combined with a HaarPooling operation to analyze the events, called HaarPooling Message Passing neural network (HMPNet).

Jet Tagging

More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference

no code implementations9 Aug 2022 Zixun Lan, Binjie Hong, Ye Ma, Fei Ma

Our critical insight into INFMCS is the strong correlation between similarity score and Maximum Common Subgraph (MCS).

Graph Classification Graph Similarity

CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer

no code implementations2 Mar 2022 Xianbin Ye, Ziliang Li, Fei Ma, Zongbi Yi, Pengyong Li, Jun Wang, Peng Gao, Yixuan Qiao, Guotong Xie

Anti-cancer drug discoveries have been serendipitous, we sought to present the Open Molecular Graph Learning Benchmark, named CandidateDrug4Cancer, a challenging and realistic benchmark dataset to facilitate scalable, robust, and reproducible graph machine learning research for anti-cancer drug discovery.

Drug Discovery Graph Learning

Maximum Likelihood Estimation for Multimodal Learning with Missing Modality

no code implementations24 Aug 2021 Fei Ma, Xiangxiang Xu, Shao-Lun Huang, Lin Zhang

Moreover, we develop a generalized form of the softmax function to effectively implement maximum likelihood estimation in an end-to-end manner.

A time-domain nearfield frequency-invariant beamforming method

no code implementations18 May 2021 Fei Ma, Thushara D. Abhayapala, Prasanga N. Samarasinghe

The time-domain implementation makes the beamformer output suitable for further use by real-time applications, the nearfield focusing enables the beamforming method to suppress an interference even if it is in the same direction as the target source, and the frequency-invariant beampattern makes the beamforming method suitable for enhancing the target source over a broad frequency band.

Speech Enhancement

Sub-GMN: The Neural Subgraph Matching Network Model

no code implementations1 Apr 2021 Zixun Lan, Limin Yu, Linglong Yuan, Zili Wu, Qiang Niu, Fei Ma

Comparing with the previous GNNs-based methods for subgraph matching task, our proposed Sub-GMN allows varying query and data graphes in the test/application stage, while most previous GNNs-based methods can only find a matched subgraph in the data graph during the test/application for the same query graph used in the training stage.

Graph Representation Learning Information Retrieval +2

A Novel Application of Image-to-Image Translation: Chromosome Straightening Framework by Learning from a Single Image

no code implementations4 Mar 2021 Sifan Song, Daiyun Huang, Yalun Hu, Chunxiao Yang, Jia Meng, Fei Ma, Frans Coenen, Jiaming Zhang, Jionglong Su

To address the flaws in the geometric algorithms, we propose a novel framework based on image-to-image translation to learn a pertinent mapping dependence for synthesizing straightened chromosomes with uninterrupted banding patterns and preserved details.

Image-to-Image Translation Translation

Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification

no code implementations30 May 2020 Fan Zhang, MinChao Yan, Chen Hu, Jun Ni, Fei Ma

In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image.

Classification General Classification +3

Relaxed Actor-Critic with Convergence Guarantees for Continuous-Time Optimal Control of Nonlinear Systems

no code implementations11 Sep 2019 Jingliang Duan, Jie Li, Qiang Ge, Shengbo Eben Li, Monimoy Bujarbaruah, Fei Ma, Dezhao Zhang

The warm-up phase minimizes the square of the Hamiltonian to achieve admissibility, while the generalized policy iteration phase relaxes the update termination conditions for faster convergence.

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