no code implementations • 30 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.
no code implementations • 29 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
no code implementations • 18 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
no code implementations • 11 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.
no code implementations • 10 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.
no code implementations • 19 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.
no code implementations • 3 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.
no code implementations • 21 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.
no code implementations • 5 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.
no code implementations • 3 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.
1 code implementation • 28 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.
no code implementations • 8 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.
no code implementations • 15 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
no code implementations • 4 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.
1 code implementation • 19 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.
no code implementations • 16 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.
no code implementations • 14 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.
no code implementations • 9 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.
1 code implementation • 24 Feb 2024 • Sipei Zhao, Fei Ma
Acoustic beamforming aims to focus acoustic signals to a specific direction and suppress undesirable interferences from other directions.
1 code implementation • 14 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.
no code implementations • 9 Feb 2024 • Zixun Lan, Binjie Hong, Jiajun Zhu, Zuo Zeng, Zhenfu Liu, Limin Yu, Fei Ma
As a semi-template-based method RetroSiG has several advantages.
no code implementations • 4 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).
no code implementations • 15 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
no code implementations • 15 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.
1 code implementation • 19 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.
1 code implementation • 15 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).
no code implementations • 12 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.
no code implementations • 1 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.
1 code implementation • 27 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.
1 code implementation • 26 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.
1 code implementation • 18 Jul 2023 • Lulu Liu, Runwei Guan, Fei Ma, Jeremy Smith, Yutao Yue
Therefore, interference mitigation is of great significance for millimeter-wave radar-based target detection.
no code implementations • 28 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.
no code implementations • 25 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).
no code implementations • 9 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).
no code implementations • 2 Apr 2022 • Daochang Wang, Fan Zhang, Fei Ma, Wei Hu, Yu Tang, Yongsheng Zhou
As a result, deep learning methods have not been fully used in airport detection tasks.
no code implementations • 2 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.
no code implementations • 26 Oct 2021 • Pengyong Li, Jun Wang, Ziliang Li, Yixuan Qiao, Xianggen Liu, Fei Ma, Peng Gao, Seng Song, Guotong Xie
Self-supervised learning has gradually emerged as a powerful technique for graph representation learning.
no code implementations • 24 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.
no code implementations • 18 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.
no code implementations • 1 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.
no code implementations • 4 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.
no code implementations • 30 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.
no code implementations • 11 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.