1 code implementation • 2 May 2024 • Tianjun Ke, Haoqun Cao, Feng Zhou
Bayesian few-shot classification has been a focal point in the field of few-shot learning.
1 code implementation • 24 Apr 2024 • Lizhi Wang, Feng Zhou, Jianqin Yin
Current scene reconstruction techniques frequently result in the loss of object detail textures and are unable to reconstruct object portions that are occluded or unseen in views.
no code implementations • 10 Apr 2024 • Zhenxi Zhang, Heng Zhou, Xiaoran Shi, Ran Ran, Chunna Tian, Feng Zhou
Additionally, the evidential fusion branch capitalizes on the complementary attributes of the first two branches and leverages an evidence-based Dempster-Shafer fusion strategy, supervised by more reliable and accurate pseudo-labels of unlabeled data.
1 code implementation • 7 Mar 2024 • Pu Cao, Feng Zhou, Qing Song, Lu Yang
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions.
no code implementations • 1 Mar 2024 • Yixuan Zhang, Feng Zhou
Fine-tuning pre-trained models is a widely employed technique in numerous real-world applications.
no code implementations • 5 Feb 2024 • Zenan Ling, Longbo Li, Zhanbo Feng, Yixuan Zhang, Feng Zhou, Robert C. Qiu, Zhenyu Liao
Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks.
no code implementations • 25 Dec 2023 • Feng Zhou, Jianqin Yin, Peiyang Li
In the second stage, we allow the keypoints to further emphasize the retained critical image features.
no code implementations • 14 Dec 2023 • Yixuan Zhang, Boyu Li, Zenan Ling, Feng Zhou
In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning.
1 code implementation • 13 Dec 2023 • Pu Cao, Lu Yang, Feng Zhou, Tianrui Huang, Qing Song
In this work, we present the task of customizing large-scale diffusion priors for specific concepts as concept-centric personalization.
1 code implementation • 13 Oct 2023 • Haojing Huang, Jingheng Ye, Qingyu Zhou, Yinghui Li, Yangning Li, Feng Zhou, Hai-Tao Zheng
In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end fashion.
1 code implementation • 9 Sep 2023 • Feng Zhou, Antonio Cicone, Haomin Zhou
Time-frequency analysis is an important and challenging task in many applications.
no code implementations • 8 Sep 2023 • Changming Xiao, Qi Yang, Feng Zhou, ChangShui Zhang
Experiments in various situations demonstrate the advantages of our method compared to strong baselines on this task.
Ranked #10 on Weakly-Supervised Semantic Segmentation on PASCAL VOC 2012 test (using extra training data)
no code implementations • 30 Aug 2023 • Zhanbo Feng, Zenan Ling, Ci Gong, Feng Zhou, Jie Li, Robert C. Qiu
Existing works tend to use either image-guided methods, which provide a visual reference but lack control over semantic coherence, or text-guided methods, which ensure faithfulness to text guidance but lack visual quality.
1 code implementation • 29 Aug 2023 • Feng Zhou, Quyu Kong, Zhijie Deng, Fengxiang He, Peng Cui, Jun Zhu
This paper presents a novel extension of multi-task Gaussian Cox processes for modeling multiple heterogeneous correlated tasks jointly, e. g., classification and regression, via multi-output Gaussian processes (MOGP).
no code implementations • 17 Aug 2023 • Yuanzhen Luo, Qingyu Zhou, Feng Zhou
Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document.
no code implementations • 18 Jul 2023 • Yinghui Li, Haojing Huang, Shirong Ma, Yong Jiang, Yangning Li, Feng Zhou, Hai-Tao Zheng, Qingyu Zhou
Recently, the development and progress of Large Language Models (LLMs) have amazed the entire Artificial Intelligence community.
1 code implementation • 4 Jul 2023 • Feng Zhou, Antonio Cicone, Haomin Zhou
Inspired by the successful applications of deep learning in fields like image processing and natural language processing, and given the lack in the literature of works in which deep learning techniques are used directly to decompose non-stationary signals into simple oscillatory components, we use the convolutional neural network, residual structure and nonlinear activation function to compute in an innovative way the local average of the signal, and study a new non-stationary signal decomposition method under the framework of deep learning.
no code implementations • 13 Mar 2023 • Jiajun Fu, Yonghao Dang, Ruoqi Yin, Shaojie Zhang, Feng Zhou, Wending Zhao, Jianqin Yin
This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop.
no code implementations • 22 Nov 2022 • Jiangfan Deng, Dewen Fan, Xiaosong Qiu, Feng Zhou
Crowdedness caused by overlapping among similar objects is a ubiquitous challenge in the field of 2D visual object detection.
1 code implementation • 25 Oct 2022 • Han Meng, Xiaosong He, Zexing Chen, Feng Zhou
Some Natural Language Generation (NLG) tasks require both faithfulness and diversity.
1 code implementation • 23 Oct 2022 • Zhijie Deng, Feng Zhou, Jun Zhu
Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks.
no code implementations • 21 Oct 2022 • Lilit Avetisyan, Chengxin Zhang, Sue Bai, Ehsan Moradi Pari, Fred Feng, Shan Bao, Feng Zhou
To better design such a sustainable future, it is necessary to understand the trends and challenges.
no code implementations • 1 Aug 2022 • Yixuan Zhang, Feng Zhou, Zhidong Li, Yang Wang, Fang Chen
In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage.
no code implementations • 30 Jul 2022 • Jackie Ayoub, Zifei Wang, Meitang Li, Huizhong Guo, Rini Sherony, Shan Bao, Feng Zhou
Advanced driver assistance systems (ADAS) are designed to improve vehicle safety.
1 code implementation • 30 Jul 2022 • Qiang Meng, Feng Zhou
Given limited public projects in this field, codes of our method and implemented baselines are made open-source in https://github. com/IrvingMeng/SecureVector.
no code implementations • 30 Apr 2022 • Zhijie Deng, Feng Zhou, Jianfei Chen, Guoqiang Wu, Jun Zhu
In this way, we relate DE to Bayesian inference to enjoy reliable Bayesian uncertainty.
no code implementations • 17 Feb 2022 • Yuhan Yao, Yuhe Zhao, Yanxian Wei, Feng Zhou, Daigao Chen, Yuguang Zhang, Xi Xiao, Ming Li, Jianji Dong, Shaohua Yu, Xinliang Zhang
We demonstrate a fully-integrated multipurpose microwave frequency identification system on silicon-on-insulator platform.
no code implementations • ICLR 2022 • Qiang Meng, Feng Zhou, Hainan Ren, Tianshu Feng, Guochao Liu, Yuanqing Lin
The growing public concerns on data privacy in face recognition can be greatly addressed by the federated learning (FL) paradigm.
no code implementations • 23 Jan 2022 • Qiang Meng, Xinqian Gu, Xiaqing Xu, Feng Zhou
Experimentally, we demonstrate the efficiency and superiority of the BBS on the tasks of face recognition and re-identification, with both simulated and real-world datasets.
no code implementations • 12 Dec 2021 • Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski, Feng Zhou, Li Shen, Fengxiang He, DaCheng Tao
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.
no code implementations • NeurIPS 2021 • Xuhui Fan, Bin Li, Feng Zhou, Scott Sisson
The mutually-exciting Hawkes process (ME-HP) is a natural choice to model reciprocity, which is an important attribute of continuous-time edge (dyadic) data.
no code implementations • 5 Nov 2021 • Yangtao Zhang, X. Jessie Yang, Feng Zhou
The advancement in machine learning and artificial intelligence is promoting the testing and deployment of autonomous vehicles (AVs) on public roads.
no code implementations • 29 Sep 2021 • Simon Luo, Feng Zhou, Lamiae Azizi, Mahito Sugiyama
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in Poisson processes using projections into lower-dimensional space.
no code implementations • 29 Sep 2021 • Zhijie Deng, Feng Zhou, Jianfei Chen, Guoqiang Wu, Jun Zhu
Deep Ensemble (DE) is a flexible, feasible, and effective alternative to Bayesian neural networks (BNNs) for uncertainty estimation in deep learning.
1 code implementation • ICCV 2021 • Qiang Meng, Chixiang Zhang, Xiaoqiang Xu, Feng Zhou
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems.
no code implementations • 25 Jul 2021 • Qiang Meng, Xiaqing Xu, Xiaobo Wang, Yang Qian, Yunxiao Qin, Zezheng Wang, Chenxu Zhao, Feng Zhou, Zhen Lei
Despite the great success achieved by deep learning methods in face recognition, severe performance drops are observed for large pose variations in unconstrained environments (e. g., in cases of surveillance and photo-tagging).
no code implementations • 20 Jul 2021 • Jackie Ayoub, Na Du, X. Jessie Yang, Feng Zhou
Their main effects and interaction effects on takeover time were examined.
no code implementations • 7 Jul 2021 • Yixuan Zhang, Feng Zhou, Zhidong Li, Yang Wang, Fang Chen
Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias.
no code implementations • 9 Jun 2021 • Feng Zhou, Quyu Kong, Yixuan Zhang, Cheng Feng, Jun Zhu
Hawkes processes are a class of point processes that have the ability to model the self- and mutual-exciting phenomena.
1 code implementation • AAAI Conference on Artificial Intelligence 2021 • Zengqun Zhao, Qingshan Liu, Feng Zhou
This paper presents an efficiently robust facial expression recognition (FER) network, named EfficientFace, which holds much fewer parameters but more robust to the FER in the wild.
Ranked #1 on Facial Expression Recognition (FER) on CAER
no code implementations • 4 Apr 2021 • Shijie Ren, Feng Zhou, Changlong Wang
Although various clustering methods have been successfully applied to polarimetric synthetic aperture radar (PolSAR) image clustering tasks, most of the available approaches fail to realize automatic determination of cluster number, nor have they derived an exact distribution for the number of looks.
2 code implementations • CVPR 2021 • Qiang Meng, Shichao Zhao, Zhida Huang, Feng Zhou
This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
no code implementations • 3 Mar 2021 • Feng Zhou, Areen Alsaid, Mike Blommer, Reates Curry, Radhakrishnan Swaminathan, Dev Kochhar, Walter Talamonti, Louis Tijerina
Research indicates that monotonous automated driving increases the incidence of fatigued driving.
no code implementations • 1 Mar 2021 • Jackie Ayoub, X. Jessie Yang, Feng Zhou
By augmenting the data using back-translation, we doubled the sample size of the dataset and the DistilBERT model was able to obtain good performance (accuracy: 0. 972; areas under the curve: 0. 993) in detecting misinformation about COVID-19.
no code implementations • 22 Feb 2021 • Mingmin Zhong, Ying Liu, Feng Zhou, Minquan Kuang, Tie Yang, Xiaotian Wang, Gang Zhang
However, these materials are uncommon because these excitations in electronic systems are usually broken by spin-orbit coupling (SOC) and normally far from the Fermi level.
Materials Science
no code implementations • 10 Feb 2021 • Xiaqing Xu, Qiang Meng, Yunxiao Qin, Jianzhu Guo, Chenxu Zhao, Feng Zhou, Zhen Lei
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing.
1 code implementation • ICCV 2021 • Junfeng Wan, Jiangfan Deng, Xiaosong Qiu, Feng Zhou
Detecting pedestrians and their associated faces jointly is a challenging task. On one hand, body or face could be absent because of occlusion or non-frontal human pose. On the other hand, the association becomes difficult or even miss-leading in crowded scenes due to the lack of strong correlational evidence.
no code implementations • NeurIPS Workshop DL-IG 2020 • Simon Luo, Feng Zhou, Lamiae Azizi, Mahito Sugiyama
Learning of the model is achieved via convex optimization, thanks to the dually flat statistical manifold generated by the log-linear model.
no code implementations • 23 Aug 2020 • Zhida Huang, Kaiyu Yue, Jiangfan Deng, Feng Zhou
Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference.
1 code implementation • ECCV 2020 • Kaiyu Yue, Jiangfan Deng, Feng Zhou
However, this introduces two problems: a) The adaptation module brings more parameters into training.
no code implementations • 30 Jun 2020 • Feng Zhou, Tao Chen, Baiying Lei
Amid the ongoing COVID-19 pandemic, whether COVID-19 patients with high risks can be recovered or not depends, to a large extent, on how early they will be treated appropriately before irreversible consequences are caused to the patients by the virus.
no code implementations • ICLR 2021 • Feng Zhou, Yixuan Zhang, Jun Zhu
Hawkes process provides an effective statistical framework for analyzing the time-dependent interaction of neuronal spiking activities.
no code implementations • 16 Jun 2020 • Simon Luo, Feng Zhou, Lamiae Azizi, Mahito Sugiyama
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in stochastic processes using lower dimensional projections.
6 code implementations • CVPR 2020 • Zezheng Wang, Zitong Yu, Chenxu Zhao, Xiangyu Zhu, Yunxiao Qin, Qiusheng Zhou, Feng Zhou, Zhen Lei
Depth supervised learning has been proven as one of the most effective methods for face anti-spoofing.
6 code implementations • CVPR 2020 • Zitong Yu, Chenxu Zhao, Zezheng Wang, Yunxiao Qin, Zhuo Su, Xiaobai Li, Feng Zhou, Guoying Zhao
Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information.
Ranked #4 on Face Anti-Spoofing on OULU-NPU
no code implementations • 12 Feb 2020 • Dong Wang, Feng Zhou, Zheng Yan, Guang Yao, Zongxuan Liu, Wennan Ma, Cewu Lu
Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features.
no code implementations • 13 Jan 2020 • Na Du, Feng Zhou, Elizabeth Pulver, Dawn M. Tilbury, Lionel P. Robert, Anuj K. Pradhan, X. Jessie Yang
Participants with different levels of emotional valence and arousal were required to take over control from automated driving, and their takeover time and quality were analyzed.
no code implementations • 29 Oct 2019 • Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen
In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP).
1 code implementation • ICCV 2019 • Xiangyun Zhao, Yi Yang, Feng Zhou, Xiao Tan, Yuchen Yuan, Yingze Bao, Ying Wu
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
no code implementations • 29 May 2019 • Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen
In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility.
no code implementations • 29 Apr 2019 • Yunxiao Qin, Chenxu Zhao, Xiangyu Zhu, Zezheng Wang, Zitong Yu, Tianyu Fu, Feng Zhou, Jingping Shi, Zhen Lei
Therefore, we define face anti-spoofing as a zero- and few-shot learning problem.
2 code implementations • NeurIPS 2018 • Kaiyu Yue, Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding, Fuxin Xu
The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos.
no code implementations • ECCV 2018 • Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma
Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.
Ranked #12 on Action Recognition on ActivityNet
2 code implementations • 19 Oct 2018 • Yaming Wang, Xiao Tan, Yi Yang, Ziyu Li, Xiao Liu, Feng Zhou, Larry S. Davis
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
no code implementations • 20 Aug 2018 • Feng Zhou, Renlong Hang, Qingshan Liu, Xiaotong Yuan
Specifically, for each pixel, we feed its spectral values in different channels into Spectral LSTM one by one to learn the spectral feature.
1 code implementation • ECCV 2018 • Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding
Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them.
Ranked #59 on Fine-Grained Image Classification on Stanford Cars
2 code implementations • 12 Jun 2018 • Yaming Wang, Xiao Tan, Yi Yang, Xiao Liu, Errui Ding, Feng Zhou, Larry S. Davis
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
no code implementations • 2 May 2018 • Feng Zhou, Shu Kong, Charless Fowlkes, Tao Chen, Baiying Lei
Specifically, we first mapped facial expressions into dimensional measures so that we transformed facial expression analysis from a classification problem to a regression one.
1 code implementation • ICCV 2017 • Jian Wang, Feng Zhou, Shilei Wen, Xiao Liu, Yuanqing Lin
The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images.
no code implementations • CVPR 2017 • Yin Cui, Feng Zhou, Jiang Wang, Xiao Liu, Yuanqing Lin, Serge Belongie
We demonstrate how to approximate kernels such as Gaussian RBF up to a given order using compact explicit feature maps in a parameter-free manner.
1 code implementation • 1 May 2017 • Xiangyong Cao, Feng Zhou, Lin Xu, Deyu Meng, Zongben Xu, John Paisley
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework.
Ranked #13 on Hyperspectral Image Classification on Indian Pines (Overall Accuracy metric, using extra training data)
1 code implementation • 30 Mar 2017 • Zhichao Li, Yi Yang, Xiao Liu, Feng Zhou, Shilei Wen, Wei Xu
We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).
1 code implementation • 23 Mar 2017 • Qingshan Liu, Feng Zhou, Renlong Hang, Xiao-Tong Yuan
In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it.
no code implementations • 3 May 2016 • Xiang Yu, Feng Zhou, Manmohan Chandraker
We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects.
no code implementations • 22 Mar 2016 • Xiao Liu, Tian Xia, Jiang Wang, Yi Yang, Feng Zhou, Yuanqing Lin
Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses.
no code implementations • CVPR 2016 • Yin Cui, Feng Zhou, Yuanqing Lin, Serge Belongie
To demonstrate the effectiveness of the proposed framework, we bootstrap a fine-grained flower dataset with 620 categories from Instagram images.
no code implementations • CVPR 2016 • Xiaofan Zhang, Feng Zhou, Yuanqing Lin, Shaoting Zhang
However, previous studies have rarely focused on learning a fined-grained and structured feature representation that is able to locate similar images at different levels of relevance, e. g., discovering cars from the same make or the same model, both of which require high precision.
no code implementations • CVPR 2016 • Feng Zhou, Yuanqing Lin
To facilitate the study, we construct a new food benchmark dataset, which consists of 37, 885 food images collected from 6 restaurants and totally 975 menus.
no code implementations • CVPR 2014 • Feng Zhou, Sing Bing Kang, Michael F. Cohen
We describe a new approach for generating regular-speed, low-frame-rate (LFR) video from a high-frame-rate (HFR) input while preserving the important moments in the original.
Ranked #6 on Video Salient Object Detection on DAVSOD-Difficult20 (using extra training data)
no code implementations • CVPR 2013 • Feng Zhou, Fernando de la Torre
This paper proposes deformable graph matching (DGM), an extension of GM for matching graphs subject to global rigid and non-rigid geometric constraints.
no code implementations • NeurIPS 2009 • Feng Zhou, Fernando Torre
Alignment of time series is an important problem to solve in many scientific disciplines.