no code implementations • 30 Mar 2023 • Yuting Gao, Jinfeng Liu, Zihan Xu, Tong Wu, Wei Liu, Jie Yang, Ke Li, Xing Sun
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks.
2 code implementations • 24 Mar 2023 • Ye Zhu, Jie Yang, Si-Qi Liu, Ruimao Zhang
Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations.
1 code implementation • 9 Mar 2023 • Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
Ranked #1 on
Zero-Shot Object Detection
on MSCOCO
1 code implementation • 23 Feb 2023 • Jiageng Wu, Xian Wu, Yining Hua, Shixu Lin, Yefeng Zheng, Jie Yang
Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression.
no code implementations • 16 Feb 2023 • Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang
We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.
1 code implementation • 14 Feb 2023 • Shuhao Shi, Kai Qiao, Jie Yang, Baojie Song, Jian Chen, Bin Yan
Specifically, node features are first mapped to a feature space through neighborhood aggregation and then generated samples for the minority class in the feature space.
no code implementations • 10 Feb 2023 • Zhen Wang, Peide Zhu, Jie Yang
Controversy is widespread online.
no code implementations • 5 Feb 2023 • Zuopeng Yang, Tianshu Chu, Xin Lin, Erdun Gao, Daqing Liu, Jie Yang, Chaoyue Wang
The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process.
1 code implementation • 3 Feb 2023 • Jie Yang, Ailing Zeng, Shilong Liu, Feng Li, Ruimao Zhang, Lei Zhang
This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.
Ranked #2 on
Multi-Person Pose Estimation
on CrowdPose
(using extra training data)
no code implementations • 4 Jan 2023 • Yankun Xu, Jie Yang, Wenjie Ming, Shuang Wang, Mohamad Sawan
In this manuscript, we propose a novel deep learning (DL)-based framework intended for obtaining short latency in real-time electroencephalogram-based epileptic seizure detection using multiscale 3D convolutional neural networks.
1 code implementation • 3 Jan 2023 • Shuhao Shi, Kai Qiao, Jian Chen, Shuai Yang, Jie Yang, Baojie Song, Linyuan Wang, Bin Yan
However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.
Ranked #1 on
Stance Detection
on MGTAB
1 code implementation • 1 Dec 2022 • Yulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen, Bo Ren, Yun Gu, Jie Yang, Chunhua Shen
Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.
no code implementations • 28 Nov 2022 • Jinbo Chen, Hui Wu, Jie Yang, Mohamad Sawan
A bio-inspired Neuron-ADC with reconfigurable sampling and static power reduction for biomedical applications is proposed in this work.
no code implementations • 27 Nov 2022 • Jie Yang, Baibhab Chatterjee, Mohammad Abu Khater, Mattias Thorsell, Sten E. Gunnarsson, Tero Kiuru, Shreyas Sen
The system permits an LNA power consumption to tune from 500 mW to 2 W (4X increase) in order to adjust the linearity from P\textsubscript{1dB, IN}=-10. 5 dBm to 0. 5 dBm (>10X increase).
1 code implementation • 20 Nov 2022 • Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple deep neural networks (DNNs) has shown state-of-the-art performances.
no code implementations • 13 Nov 2022 • Qingcheng Zeng, Lucas Garay, Peilin Zhou, Dading Chong, Yining Hua, Jiageng Wu, Yikang Pan, Han Zhou, Jie Yang
While large pre-trained models have transformed the field of natural language processing (NLP), the high training cost and low cross-lingual availability of such models prevent the new advances from being equally shared by users across all languages, especially the less spoken ones.
1 code implementation • 11 Nov 2022 • Lingtong Kong, Jie Yang
To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement.
no code implementations • 11 Nov 2022 • Lingtong Kong, Jinfeng Liu, Jie Yang
Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation.
no code implementations • 2 Nov 2022 • Da Chen, Nima Emami, Shahed Rezaei, Philipp L. Rosendahl, Bai-Xiang Xu, Jens Schneider, Kang Gao, Jie Yang
The error range of CNN models leads to an uncertain mechanical performance, which is further evaluated in a structural uncertainty analysis on the FG porous three-layer beam consisting of two thin high-density layers and a thick low-density one, where the imprecise CNN predicted moduli are represented as triangular fuzzy numbers in double parametric form.
no code implementations • 20 Oct 2022 • Yichao Wang, Jie Yang
In this paper, we present, Wi-Mesh, a WiFi vision-based 3D human mesh construction system.
1 code implementation • 19 Oct 2022 • Pengjin Wei, Guohang Yan, Yikang Li, Kun Fang, Jie Yang, Wei Liu
This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks.
1 code implementation • 17 Oct 2022 • Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, Jie Yang
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption.
no code implementations • 16 Oct 2022 • Yuanyuan Qiao, Jiaxin Yin, Wei Wang, Fábio Duarte, Jie Yang, Carlo Ratti
Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error.
no code implementations • 3 Oct 2022 • Di wu, Jie Yang, Mohamad Sawan
In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications.
no code implementations • 30 Sep 2022 • Yili Ren, Jie Yang
In particular, we leverage multiple antennas on next-generation WiFi devices and 2D AoA estimation of the signal reflections to enable WiFi to visualize a person in the physical environment.
no code implementations • 30 Sep 2022 • Burcu Sayin, Fabio Casati, Andrea Passerini, Jie Yang, Xinyue Chen
In this paper, we argue that the way we have been training and evaluating ML models has largely forgotten the fact that they are applied in an organization or societal context as they provide value to people.
1 code implementation • 28 Sep 2022 • Peilin Zhou, Zeqiang Wang, Dading Chong, Zhijiang Guo, Yining Hua, Zichang Su, Zhiyang Teng, Jiageng Wu, Jie Yang
To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9, 101 entities (in 5, 278 tweets).
1 code implementation • 28 Sep 2022 • Zeqiang Wang, Yile Wang, Jiageng Wu, Zhiyang Teng, Jie Yang
Designed in a hierarchical structure, YATO supports free combinations of three types of features including 1) traditional neural networks (CNN, RNN, etc.
no code implementations • 26 Sep 2022 • Chaoming Fang, Ziyang Shen, Fengshi Tian, Jie Yang, Mohamad Sawan
In this design, a compact online learning neuromorphic hardware architecture with ultra-low power consumption designed explicitly for biosignal processing is proposed.
no code implementations • 16 Sep 2022 • Chuanqing Wang, Chaoming Fang, Yong Zou, Jie Yang, Mohamad Sawan
In this paper, we propose an energy-efficient dynamic scenes processing framework (SpikeSEE) that combines a spike representation encoding technique and a bio-inspired spiking recurrent neural network (SRNN) model to achieve intelligent processing and extreme low-power computation for retinal prostheses.
no code implementations • 15 Sep 2022 • Guang Liu, Jie Yang, Ledell Wu
The learning of an effective contextual representation requires meaningful features and a large amount of data.
no code implementations • 2 Aug 2022 • Feilong Chen, Di wu, Jie Yang, Yi He
In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i. e., how to establish the uncertain relationship between sparse streaming features and labels.
no code implementations • 1 Aug 2022 • Jinfeng Liu, Lingtong Kong, Jie Yang
Video frame interpolation is a classic and challenging low-level computer vision task.
no code implementations • 23 Jul 2022 • Jie Yang, Yilin Li, Deddy Jobson
To achieve a better lift return on investment (lift ROI) on the enduring effect of the promotion and improve customer retention and loyalty, we propose a framework of multiple treatment promotion decision making by modeling each customer's direct and enduring response.
1 code implementation • 29 Jun 2022 • Yining Hua, Hang Jiang, Shixu Lin, Jie Yang, Joseph M. Plasek, David W. Bates, Li Zhou
Time-trend analysis revealed that Hydroxychloroquine and Ivermectin received much more discussion than Molnupiravir and Remdesivir, particularly during COVID-19 surges.
1 code implementation • Pattetn Recognition 2022 • Jie Yang
We develop our DFC in an asymmetric dual network framework that consists of a generic feature extraction network and an elaborated feature estimation network, and detect the possible anomalies within images by modeling and evaluating the associated deep feature correspondence between the two dual network branches.
Ranked #1 on
Anomaly Detection
on BottleCap
(using extra training data)
no code implementations • 26 Jun 2022 • Qingcheng Zeng, Dading Chong, Peilin Zhou, Jie Yang
Accented speech recognition and accent classification are relatively under-explored research areas in speech technology.
1 code implementation • 23 Jun 2022 • Weijie Ma, Ye Zhu, Ruimao Zhang, Jie Yang, Yiwen Hu, Zhen Li, Li Xiang
By aligning the class tokens and spatial attention maps of paired NBI and WL images at different levels, the Transformer achieves the ability to keep both global and local representation consistency for the above two modalities.
2 code implementations • 22 Jun 2022 • Zhu Sun, Hui Fang, Jie Yang, Xinghua Qu, Hongyang Liu, Di Yu, Yew-Soon Ong, Jie Zhang
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
no code implementations • 21 Jun 2022 • Jie Yang, Ye Zhu, Ruimao Zhang, Chaoqun Wang, Zhen Li, Xiang Wan
Different from previous methods which adopted both modality-specific and modality-shared modules to accommodate the appearance variance of different modalities while extracting the common semantic information, our method is based on a single Transformer with a carefully designed External Attention Module (EAM) to learn the structured semantic consistency (i. e. semantic class representations and their correlations) between modalities in the training phase.
1 code implementation • 16 Jun 2022 • Yuanfeng Ji, Haotian Bai, Jie Yang, Chongjian Ge, Ye Zhu, Ruimao Zhang, Zhen Li, Lingyan Zhang, Wanling Ma, Xiang Wan, Ping Luo
Constraint by the high cost of collecting and labeling 3D medical data, most of the deep learning models to date are driven by datasets with a limited number of organs of interest or samples, which still limits the power of modern deep models and makes it difficult to provide a fully comprehensive and fair estimate of various methods.
no code implementations • 8 Jun 2022 • Shiqi Zhao, Jie Yang, Yankun Xu, Mohamad Sawan
Nowadays, several deep learning methods are proposed to tackle the challenge of epileptic seizure prediction.
1 code implementation • CVPR 2022 • Zuopeng Yang, Daqing Liu, Chaoyue Wang, Jie Yang, DaCheng Tao
Compared to existing CNN-based and Transformer-based generation models that entangled modeling on pixel-level&patch-level and object-level&patch-level respectively, the proposed focal attention predicts the current patch token by only focusing on its highly-related tokens that specified by the spatial layout, thereby achieving disambiguation during training.
2 code implementations • CVPR 2022 • Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Xiaoming Huang, Ying Tai, Chengjie Wang, Jie Yang
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications.
Ranked #1 on
Video Frame Interpolation
on Middlebury
no code implementations • 27 May 2022 • Jinbo Chen, Mahdi Tarkhan, Hui Wu, Fereidoon Hashemi Noshahr, Jie Yang, Mohamad Sawan
Recent years have seen fast advances in neural recording circuits and systems as they offer a promising way to investigate real-time brain monitoring and the closed-loop modulation of psychological disorders and neurodegenerative diseases.
no code implementations • 26 May 2022 • Jinbo Chen, Fengshi Tian, Jie Yang, Mohamad Sawan
Wearable electrocardiograph (ECG) recording and processing systems have been developed to detect cardiac arrhythmia to help prevent heart attacks.
no code implementations • 12 May 2022 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Jocelyn Chanussot, Jie Yang
In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions.
no code implementations • 29 Apr 2022 • Yankun Xu, Jie Yang, Mohamad Sawan
To identify the preictal region that precedes the onset of seizure, a large number of annotated EEG signals are required to train DL algorithms.
1 code implementation • 20 Apr 2022 • Di wu, Siyuan Li, Jie Yang, Mohamad Sawan
Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.
no code implementations • 16 Apr 2022 • Yili Ren, Jie Yang
This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses WiFi devices at home.
1 code implementation • 15 Apr 2022 • Linyi Yang, Zhen Wang, Yuxiang Wu, Jie Yang, Yue Zhang
Understanding causality is key to the success of NLP applications, especially in high-stakes domains.
1 code implementation • 7 Mar 2022 • Pengjin Wei, Guohang Yan, Yikang Li, Kun Fang, Xinyu Cai, Jie Yang, Wei Liu
Sensor-based environmental perception is a crucial part of the autonomous driving system.
no code implementations • 25 Feb 2022 • Di wu, Jie Yang, Mohamad Sawan
The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.
no code implementations • 22 Feb 2022 • Jie Yang, Qinghe Du, Yi Jiang
As an interesting by-product, we propose an enhancement to the BLE standard by introducing a bit interleaver to its physical layer; the resultant improvement of the receiver sensitivity can make it a better fit for some Internet of Things (IoT) communications.
no code implementations • 18 Feb 2022 • Huihui Fang, Fei Li, Junde Wu, Huazhu Fu, Xu sun, Jaemin Son, Shuang Yu, Menglu Zhang, Chenglang Yuan, Cheng Bian, Baiying Lei, Benjian Zhao, Xinxing Xu, Shaohua Li, Francisco Fumero, José Sigut, Haidar Almubarak, Yakoub Bazi, Yuanhao Guo, Yating Zhou, Ujjwal Baid, Shubham Innani, Tianjiao Guo, Jie Yang, José Ignacio Orlando, Hrvoje Bogunović, Xiulan Zhang, Yanwu Xu
Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge -- Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2).
no code implementations • 9 Feb 2022 • Lu Wang, Jie Yang, Masoumeh Zareapoor, ZhongLong Zheng
Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.
no code implementations • 29 Jan 2022 • Weihao Yu, Hao Zheng, Minghui Zhang, Hanxiao Zhang, Jiayuan Sun, Jie Yang
Since the volume of the peripheral bronchi may be much smaller than the large branches in an input patch, the common segmentation loss is not sensitive to the breakages among the distal branches.
no code implementations • 13 Dec 2021 • Fabio Casati, Pierre-André Noël, Jie Yang
We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by their model in practical applications.
no code implementations • 30 Nov 2021 • Garrett Allen, Jie Yang, Maria Soledad Pera, Ujwal Gadiraju
Further, we discuss preliminary ideas on strategies for evaluation.
no code implementations • 11 Nov 2021 • Burcu Sayin, Jie Yang, Andrea Passerini, Fabio Casati
We motivate why the science of learning to reject model predictions is central to ML, and why human computation has a lead role in this effort.
no code implementations • NeurIPS 2021 • Jia-Heng Tang, Weikai Chen, Jie Yang, Bo wang, Songrun Liu, Bo Yang, Lin Gao
We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.
no code implementations • 26 Oct 2021 • Di wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
no code implementations • 19 Oct 2021 • Zhenyuan Zhong, Jie Yang, Yacong Ma, Shoubin Dong, Jinlong Hu
The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial features from a large number of categorical features while preserving the interpretability of the method.
no code implementations • 19 Oct 2021 • Heng Fan, Jiaxiang Ren, Jie Yang, Yi-Xian Qin, Haibin Ling
The aim of this study was to investigate whether a deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs.
no code implementations • 18 Oct 2021 • Hossein A. Rahmani, Jie Yang
Key Opinion Leaders (KOLs) are people that have a strong influence and their opinions are listened to by people when making important decisions.
no code implementations • 15 Oct 2021 • Yili Ren, Jie Yang
Our system tracks free-form activity by estimating a 3D skeleton pose that consists of a set of joints of the human body.
no code implementations • 27 Sep 2021 • Xun Yao, Junlong Ma, Xinrong Hu, Junping Liu, Jie Yang, Wanqing Li
The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer.
no code implementations • 27 Sep 2021 • Jie Yang, Ruijie Xu, Zhiquan Qi, Yong Shi
Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision.
2 code implementations • 13 Sep 2021 • Kai Li, Jie Yang, Siwei Ma, Bo wang, Shanshe Wang, Yingjie Tian, Zhiquan Qi
For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet.
1 code implementation • LREC 2022 • Zhen Wang, Xu Shan, Xiangxie Zhang, Jie Yang
Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification.
Ranked #1 on
News Classification
on N15News
no code implementations • 18 Aug 2021 • Pourya Shamsolmoali, Jocelyn Chanussot, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang
Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing.
no code implementations • 17 Aug 2021 • Yankun Xu, Jie Yang, Shiqi Zhao, Hemmings Wu, Mohamad Sawan
Conventional seizure prediction works usually rely on features extracted from Electroencephalography (EEG) recordings and classification algorithms such as regression or support vector machine (SVM) to locate the short time before seizure onset.
1 code implementation • 15 Jul 2021 • Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Michael Ng
The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.
1 code implementation • 5 Jul 2021 • Ziyi Liu, Jie Yang, Svetlana Yanushkevich, Orly Yadid-Pecht
Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.
no code implementations • 24 Jun 2021 • Yulei Qin, Yun Gu, Hanxiao Zhang, Jie Yang, Lihui Wang, Zhexin Wang, Feng Yao, Yue-Min Zhu
The correlation between nodules and the counting number of airways and vessels that contact or project towards nodules are respectively (OR=22. 96, \chi^2=105. 04) and (OR=7. 06, \chi^2=290. 11).
no code implementations • 18 Jun 2021 • Yili Ren, Jie Yang
Among those services, sensing the liquid level in a container is critical to building many smart home and mobile healthcare applications that improve the quality of life.
no code implementations • 7 Jun 2021 • Kuikun Liu, Jie Yang, Cai Sun, Haoyuan Chi
Currently, instance segmentation is attracting more and more attention in machine learning region.
no code implementations • 2 Jun 2021 • Pourya Shamsolmoali, Masoumeh Zareapoor, Jocelyn Chanussot, Huiyu Zhou, Jie Yang
The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach.
no code implementations • IEEE International Conference on Acoustics, Speech and Signal Processing 2021 • Ning Lv, Xuezhi Xiang, Xinyao Wang, Jie Yang, Rokia Abdeen, Abdulmotaleb El Saddik
In order to process divergence between detection and re-identification, we introduce switchable normalization and gradient centralization to improve the stability of the model.
no code implementations • 5 May 2021 • Ziyu Wang, Jie Yang, Mohamad Sawan
Accurate prediction of epileptic seizures allows patients to take preventive measures in advance to avoid possible injuries.
1 code implementation • 3 May 2021 • Jing Huang, Jie Yang
In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs.
1 code implementation • 2 May 2021 • Jing Huang, Xiaolin Huang, Jie Yang
Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.
1 code implementation • 13 Apr 2021 • Qin Luo, Kun Fang, Jie Yang, Xiaolin Huang
Random Fourier Features (RFF) demonstrate wellappreciated performance in kernel approximation for largescale situations but restrict kernels to be stationary and positive definite.
1 code implementation • 8 Mar 2021 • Lingtong Kong, Chunhua Shen, Jie Yang
Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only 1/10 computation of comparable networks to achieve on par accuracy.
no code implementations • 5 Mar 2021 • Xiaohang Yang, Lingtong Kong, Jie Yang
Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding.
no code implementations • 25 Feb 2021 • Fengshi Tian, Jie Yang, Shiqi Zhao, Mohamad Sawan
Motivated by the energy-efficient spiking neural networks (SNNs), a neuromorphic computing approach for seizure prediction is proposed in this work.
no code implementations • 23 Feb 2021 • Lan Chen, Lin Gao, Jie Yang, Shibiao Xu, Juntao Ye, Xiaopeng Zhang, Yu-Kun Lai
Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes.
no code implementations • 2 Feb 2021 • Jie Yang, Mengchen Lin, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht
It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.
1 code implementation • 31 Jan 2021 • Jie Yang, Ziyi Liu, Mengchen Lin, Svetlana Yanushkevich, Orly Yadid-Pecht
The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.
no code implementations • 31 Jan 2021 • Lingtong Kong, Xiaohang Yang, Jie Yang
Optical flow estimation is an essential step for many real-world computer vision tasks.
1 code implementation • 31 Jan 2021 • Jie Yang, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht
HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.
no code implementations • 16 Jan 2021 • Jie Yang, Soyeon Caren Han, Josiah Poon
Existing causality extraction techniques include knowledge-based, statistical machine learning(ML)-based, and deep learning-based approaches.
no code implementations • 11 Jan 2021 • Ziyi Liu, Jie Yang, Mengchen Lin, Kenneth Kam Fai Lai, Svetlana Yanushkevich, Orly Yadid-Pecht
Furthermore, we show the effect of different face detection procedures on the WDRIs in our database.
no code implementations • ICCV 2021 • Ming-Xian Lin, Jie Yang, He Wang, Yu-Kun Lai, Rongfei Jia, Binqiang Zhao, Lin Gao
Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning.
1 code implementation • 26 Dec 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Huiyu Zhou, Ruili Wang, M. Emre Celebi, Jie Yang
However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training.
1 code implementation • 13 Dec 2020 • Jie Yang, Yong Shi, Zhiquan Qi
Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.
Ranked #43 on
Anomaly Detection
on MVTec AD
no code implementations • 10 Dec 2020 • Yulei Qin, Hao Zheng, Yun Gu, Xiaolin Huang, Jie Yang, Lihui Wang, Feng Yao, Yue-Min Zhu, Guang-Zhong Yang
Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.
no code implementations • 4 Dec 2020 • Jie Yang, Lin Gao, Qingyang Tan, Yihua Huang, Shihong Xia, Yu-Kun Lai
The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales.
1 code implementation • 26 Nov 2020 • Jie Yang
Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.
1 code implementation • 24 Nov 2020 • Hao Zheng, Yulei Qin, Yun Gu, Fangfang Xie, Jie Yang, Jiayuan Sun, Guang-Zhong Yang
Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways.
2 code implementations • 23 Oct 2020 • Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang
Despite of the efficiency in defending specific attacks, adversarial training is benefited from the data augmentation, which does not contribute to the robustness of DNN itself and usually suffers from accuracy drop on clean data as well as inefficiency in unknown attacks.
no code implementations • 22 Oct 2020 • Zaid Nabulsi, Andrew Sellergren, Shahar Jamshy, Charles Lau, Edward Santos, Atilla P. Kiraly, Wenxing Ye, Jie Yang, Rory Pilgrim, Sahar Kazemzadeh, Jin Yu, Sreenivasa Raju Kalidindi, Mozziyar Etemadi, Florencia Garcia-Vicente, David Melnick, Greg S. Corrado, Lily Peng, Krish Eswaran, Daniel Tse, Neeral Beladia, Yun Liu, Po-Hsuan Cameron Chen, Shravya Shetty
To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States.
no code implementations • 22 Oct 2020 • Kexin Lv, Fan He, Xiaolin Huang, Jie Yang, Liming Chen
Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.
1 code implementation • 2 Oct 2020 • Rao Fu, Jie Yang, Jiawei Sun, Fang-Lue Zhang, Yu-Kun Lai, Lin Gao
Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures.
no code implementations • 28 Sep 2020 • Jie Yang, Jing Xu, Xiao Li, Shi Jin, Bo Gao
As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.
no code implementations • 28 Sep 2020 • Kun Fang, Xiaolin Huang, Yingwen Wu, Tao Li, Jie Yang
To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.
no code implementations • 19 Sep 2020 • Sheng Wan, Chen Gong, Shirui Pan, Jie Yang, Jian Yang
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.
1 code implementation • 10 Sep 2020 • Kun Fang, Fanghui Liu, Xiaolin Huang, Jie Yang
In the second-stage process, a linear learner is conducted with respect to the mapped random features.
1 code implementation • 7 Sep 2020 • Ruixiao Sun, Jie Yang, Mehrdad Yousefzadeh
Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community.
1 code implementation • 12 Aug 2020 • Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao
While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner.
1 code implementation • 10 Aug 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Ruili Wang, Jie Yang
We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects.
no code implementations • 7 Aug 2020 • Masoumeh Zareapoor, Pourya Shamsolmoali, Jie Yang
In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution.
no code implementations • 9 Jul 2020 • Jie Yang, Elsa D. Angelini, Pallavi P. Balte, Eric A. Hoffman, John H. M. Austin, Benjamin M. Smith, R. Graham Barr, Andrew F. Laine
Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy.
no code implementations • 22 Jun 2020 • Lingtong Kong, Jie Yang
Significant progress has been made for estimating optical flow using deep neural networks.
Ranked #4 on
Optical Flow Estimation
on KITTI 2012
no code implementations • 1 Jun 2020 • Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens
In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).
no code implementations • CVPR 2020 • Jie Yang, Jiarou Fan, Yiru Wang, Yige Wang, Weihao Gan, Lin Liu, Wei Wu
Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc.
1 code implementation • ECCV 2020 • Xiyang Liu, Jie Yang, Wenrui Ding
The crowd counting task aims at estimating the number of people located in an image or a frame from videos.
1 code implementation • 6 May 2020 • Fan He, Kexin Lv, Jie Yang, Xiaolin Huang
This letter proposes a one-shot algorithm for feature-distributed kernel PCA.
no code implementations • 27 Apr 2020 • Jie Yang, Chin-Teng Lin
Grouping similar objects is a fundamental tool of scientific analysis, ubiquitous in disciplines from biology and chemistry to astronomy and pattern recognition.
no code implementations • 23 Apr 2020 • Jia Cai, Kexin Lv, Junyi Huo, Xiaolin Huang, Jie Yang
To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures.
no code implementations • 5 Apr 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Linlin Shen, Abdul Hamid Sadka, Jie Yang
It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples.
no code implementations • 19 Mar 2020 • Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang
In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.
1 code implementation • 18 Mar 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang
The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models.
no code implementations • 17 Mar 2020 • Pourya Shamsolmoali, Masoumeh Zareapoor, Ruili Wang, Huiyu Zhou, Jie Yang
This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images.
1 code implementation • 11 Feb 2020 • Jie Yang, Zhiquan Qi, Yong Shi
This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works.
no code implementations • 16 Jan 2020 • Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang, Xiaolin Huang
AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.
no code implementations • 14 Jan 2020 • Lu Wang, Jie Yang
Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities.
no code implementations • 29 Dec 2019 • Tianshu Chu, Qin Luo, Jie Yang, Xiaolin Huang
In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.
no code implementations • 19 Dec 2019 • Xiao Han, ZiHao Wang, Enmei Tu, Gunnam Suryanarayana, Jie Yang
Deep learning demands a huge amount of well-labeled data to train the network parameters.
no code implementations • 17 Dec 2019 • Zeyu Deng, Lihui Wang, Zixiang Kuai, Qijian Chen, Xinyu Cheng, Feng Yang, Jie Yang, Yue-Min Zhu
The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing.
no code implementations • 2 Dec 2019 • Akansha Bhardwaj, Jie Yang, Philippe Cudré-Mauroux
Such approaches are, however, limited as they fail to reliably estimate the informativeness of a keyword and its expectation for model training.
no code implementations • 27 Nov 2019 • Jie Yang, Yu-Kai Wang, Xin Yao, Chin-Teng Lin
(c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets.
no code implementations • 20 Nov 2019 • Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.
no code implementations • 11 Nov 2019 • Lu Wang, Jie Yang
Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage.
no code implementations • IJCNLP 2019 • Sepideh Mesbah, Jie Yang, Robert-Jan Sips, Manuel Valle Torre, Christoph Lofi, Aless Bozzon, ro, Geert-Jan Houben
Social media provides a timely yet challenging data source for adverse drug reaction (ADR) detection.
no code implementations • 30 Oct 2019 • Yi-Ling Qiao, Lin Gao, Jie Yang, Paul L. Rosin, Yu-Kun Lai, Xilin Chen
3D models are commonly used in computer vision and graphics.
no code implementations • 19 Sep 2019 • Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke
This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.
no code implementations • 13 Aug 2019 • Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
1 code implementation • 7 Aug 2019 • Yu-Jie Yuan, Yu-Kun Lai, Jie Yang, Hongbo Fu, Lin Gao
3D shape analysis is an important research topic in computer vision and graphics.
1 code implementation • 23 Jul 2019 • Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Ian Reid
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
no code implementations • 16 Jul 2019 • Yulei Qin, Mingjian Chen, Hao Zheng, Yun Gu, Mali Shen, Jie Yang, Xiaolin Huang, Yue-Min Zhu, Guang-Zhong Yang
Airway segmentation on CT scans is critical for pulmonary disease diagnosis and endobronchial navigation.
no code implementations • 1 Jul 2019 • Xinyang Feng, Zachary C. Lipton, Jie Yang, Scott A. Small, Frank A. Provenzano
Numerous studies have established that estimated brain age, as derived from statistical models trained on healthy populations, constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases.
no code implementations • 28 May 2019 • Enmei Tu, Jie Yang
Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning.
no code implementations • 14 May 2019 • Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Anton Van Den Hengel, Dehua Xie, Bing Zeng
Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.
no code implementations • 15 Apr 2019 • Fanghui Liu, Chen Gong, Xiaolin Huang, Tao Zhou, Jie Yang, DaCheng Tao
In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).
no code implementations • 5 Apr 2019 • Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, DaCheng Tao
As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms.
no code implementations • 5 Mar 2019 • Hafiz Tayyab Mustafa, Jie Yang, Masoumeh Zareapoor
To address the above issues, we proposed a new MFIF method, which aims to learn feature extraction, fusion and reconstruction components together to produce a complete unsupervised end-to-end trainable deep CNN.
1 code implementation • 17 Feb 2019 • Sanli Tang, Fan He, Xiaolin Huang, Jie Yang
To train the deep model, a dataset is established, namely DeepPCB, which contains 1, 500 image pairs with annotations including positions of 6 common types of PCB defects.
1 code implementation • 13 Feb 2019 • Siyan Tao, Yao Guo, Chuang Zhu, Huang Chen, Yue Zhang, Jie Yang, Jun Liu
In this paper, we propose a novel method for highly efficient follicular segmentation of thyroid cytopathological WSIs.
no code implementations • ICCV 2019 • Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, Junjie Yan
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed.
no code implementations • 28 Dec 2018 • Jie Yang, Si-Qi Liu, Sasa Grbic, Arnaud Arindra Adiyoso Setio, Zhoubing Xu, Eli Gibson, Guillaume Chabin, Bogdan Georgescu, Andrew F. Laine, Dorin Comaniciu
Synthesizing the objects of interests, such as lung nodules, in medical images based on the distribution of annotated datasets can be helpful for improving the supervised learning tasks, especially when the datasets are limited by size and class balance.
no code implementations • 19 Dec 2018 • Xinyang Feng, Jie Yang, Andrew F. Laine, Elsa D. Angelini
In neuroimaging studies, the human cortex is commonly modeled as a sphere to preserve the topological structure of the cortical surface.
no code implementations • 4 Dec 2018 • Si-Qi Liu, Eli Gibson, Sasa Grbic, Zhoubing Xu, Arnaud Arindra Adiyoso Setio, Jie Yang, Bogdan Georgescu, Dorin Comaniciu
The performance of medical image analysis systems is constrained by the quantity of high-quality image annotations.
1 code implementation • NAACL 2019 • Jie Yang, Yue Zhang, Shuailong Liang
Previous lattice LSTM model takes word embeddings as the lexicon input, we prove that subword encoding can give the comparable performance and has the benefit of not relying on any external segmentor.
1 code implementation • 13 Oct 2018 • Yulei Qin, Juan Wen, Hao Zheng, Xiaolin Huang, Jie Yang, Ning Song, Yue-Min Zhu, Lingqian Wu, Guang-Zhong Yang
To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks.
no code implementations • 26 Sep 2018 • Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.
no code implementations • 3 Sep 2018 • Sanli Tang, Xiaolin Huang, Mingjian Chen, Chengjin Sun, Jie Yang
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations.
1 code implementation • ECCV 2018 • Jie Yang, Dong Gong, Lingqiao Liu, Qinfeng Shi
Reflections often obstruct the desired scene when taking photos through glass panels.
no code implementations • 31 Aug 2018 • Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li
Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.
no code implementations • 15 Aug 2018 • Liyuan Jiang, Shuang Zhou, Keren Li, Fangfang Wang, Jie Yang
We develop a new nonparametric approach for estimating the risk-neutral density of asset prices and reformulate its estimation into a double-constrained optimization problem.
3 code implementations • ACL 2018 • Jie Yang, Yue Zhang
This paper describes NCRF++, a toolkit for neural sequence labeling.
Ranked #7 on
Chunking
on Penn Treebank
2 code implementations • COLING 2018 • Jie Yang, Shuailong Liang, Yue Zhang
We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i. e. NER, Chunking, and POS tagging).
1 code implementation • IEEE FG 2018 2018 • Guillaume Devineau, Wang Xi, Jie Yang, Fabien Moutarde
In this paper, we introduce a new 3D hand gesture recognition approach based on a deep learning model.
Ranked #4 on
Hand Gesture Recognition
on DHG-14
3 code implementations • ACL 2018 • Yue Zhang, Jie Yang
We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.
Ranked #13 on
Chinese Named Entity Recognition
on Resume NER
no code implementations • 4 May 2018 • Jie Yang, Diego Klabjan
In this paper, we propose an active learning algorithm and models which can gradually learn individual's preference through pairwise comparisons.
no code implementations • 12 Mar 2018 • Jie Yang, Thomas Drake, Andreas Damianou, Yoelle Maarek
Experiments show that our framework can accurately learn annotator expertise, infer true labels, and effectively reduce the amount of annotations in model training as compared to state-of-the-art approaches.
no code implementations • 30 Jan 2018 • Jie Yang, Pingping Zhang, Yan Liu
The numerical results show that there is not significant reduction in the classification ability of the network if the input signals are subject to sinusoidal and Gaussian perturbations.
1 code implementation • ACL 2018 • Jie Yang, Yue Zhang, Linwei Li, Xingxuan Li
And the annotation time can be further compressed by 16. 47\% through intelligent recommendation.
no code implementations • 8 Nov 2017 • Yang Hu, Yun Gu, Jie Yang, Guang-Zhong Yang
In robotic surgery, task automation and learning from demonstration combined with human supervision is an emerging trend for many new surgical robot platforms.
no code implementations • 13 Sep 2017 • Qingyang Tan, Lin Gao, Yu-Kun Lai, Jie Yang, Shihong Xia
Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing.
Graphics
no code implementations • 5 Sep 2017 • Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Leif Kobbelt, Shihong Xia
This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied.
Graphics
no code implementations • 5 Sep 2017 • Wenjie Pei, Jie Yang, Zhu Sun, Jie Zhang, Alessandro Bozzon, David M. J. Tax
In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions.