Search Results for author: Wei Zeng

Found 44 papers, 16 papers with code

Large Batch Optimization for Object Detection: Training COCO in 12 Minutes

no code implementations ECCV 2020 Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Yao-Wei Wang, Jinqiao Wang, Ming Tang

Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.

object-detection Object Detection

An Asymmetric Modeling for Action Assessment

no code implementations ECCV 2020 Jibin Gao, Wei-Shi Zheng, Jia-Hui Pan, Chengying Gao, Yao-Wei Wang, Wei Zeng, Jian-Huang Lai

However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.

Action Assessment

Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image

no code implementations ECCV 2020 Wei Zeng, Sezer Karaoglu, Theo Gevers

Leveraging the layout depth map as an intermediate representation, our proposed method outperforms existing methods for both panorama layout prediction and depth estimation.

Depth Estimation Depth Prediction

Elucidate Gender Fairness in Singing Voice Transcription

1 code implementation5 Aug 2023 Xiangming Gu, Wei Zeng, Ye Wang

Leveraging the prior knowledge that pitch distributions may contribute to the gender bias, we propose conditionally aligning acoustic representations between demographic groups by feeding note events to the attribute predictor.


TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations

1 code implementation19 Jul 2023 Jianing Hao, Qing Shi, Yilin Ye, Wei Zeng

Deep learning (DL) approaches are being increasingly used for time-series forecasting, with many efforts devoted to designing complex DL models.

Feature Engineering Navigate +3

Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model

1 code implementation28 Apr 2023 Shishi Xiao, Suizi Huang, Yue Lin, Yilin Ye, Wei Zeng

Pictorial visualization seamlessly integrates data and semantic context into visual representation, conveying complex information in a manner that is both engaging and informative.


Everyone Can Be Picasso? A Computational Framework into the Myth of Human versus AI Painting

1 code implementation17 Apr 2023 Yilin Ye, Rong Huang, Kang Zhang, Wei Zeng

The recent advances of AI technology, particularly in AI-Generated Content (AIGC), have enabled everyone to easily generate beautiful paintings with simple text description.

WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval

1 code implementation14 Apr 2023 Shishi Xiao, Yihan Hou, Cheng Jin, Wei Zeng

Retrieving charts from a large corpus is a fundamental task that can benefit numerous applications such as visualization recommendations. The retrieved results are expected to conform to both explicit visual attributes (e. g., chart type, colormap) and implicit user intents (e. g., design style, context information) that vary upon application scenarios.

Retrieval Zero-Shot Learning

Keypoint-Guided Optimal Transport

2 code implementations23 Mar 2023 Xiang Gu, Yucheng Yang, Wei Zeng, Jian Sun, Zongben Xu

In this paper, we propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL) that searches for the optimal matching (i. e., transport plan) guided by the keypoints in OT.

Domain Adaptation Image-to-Image Translation

Graph Enhanced BERT for Query Understanding

no code implementations3 Apr 2022 Juanhui Li, Yao Ma, Wei Zeng, Suqi Cheng, Jiliang Tang, Shuaiqiang Wang, Dawei Yin

In other words, GE-BERT can capture both the semantic information and the users' search behavioral information of queries.

Fault Detection and Isolation of Uncertain Nonlinear Parabolic PDE Systems

no code implementations29 Mar 2022 Jingting Zhang, Chengzhi Yuan, Wei Zeng, Cong Wang

This paper proposes a novel fault detection and isolation (FDI) scheme for distributed parameter systems modeled by a class of parabolic partial differential equations (PDEs) with nonlinear uncertain dynamics.

Decision Making Fault Detection

Neural Architecture Search With Representation Mutual Information

1 code implementation CVPR 2022 Xiawu Zheng, Xiang Fei, Lei Zhang, Chenglin Wu, Fei Chao, Jianzhuang Liu, Wei Zeng, Yonghong Tian, Rongrong Ji

Building upon RMI, we further propose a new search algorithm termed RMI-NAS, facilitating with a theorem to guarantee the global optimal of the searched architecture.

Neural Architecture Search

End-to-end Adaptive Distributed Training on PaddlePaddle

1 code implementation6 Dec 2021 Yulong Ao, Zhihua Wu, dianhai yu, Weibao Gong, Zhiqing Kui, Minxu Zhang, Zilingfeng Ye, Liang Shen, Yanjun Ma, Tian Wu, Haifeng Wang, Wei Zeng, Chao Yang

The experiments demonstrate that our framework can satisfy various requirements from the diversity of applications and the heterogeneity of resources with highly competitive performance.

Language Modelling Recommendation Systems +1

DPT: Deformable Patch-based Transformer for Visual Recognition

1 code implementation30 Jul 2021 Zhiyang Chen, Yousong Zhu, Chaoyang Zhao, Guosheng Hu, Wei Zeng, Jinqiao Wang, Ming Tang

To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches.

Image Classification object-detection +2

FloorLevel-Net: Recognizing Floor-Level Lines with Height-Attention-Guided Multi-task Learning

no code implementations6 Jul 2021 Mengyang Wu, Wei Zeng, Chi-Wing Fu

The ability to recognize the position and order of the floor-level lines that divide adjacent building floors can benefit many applications, for example, urban augmented reality (AR).

Data Augmentation Multi-Task Learning

Adaptive Class Suppression Loss for Long-Tail Object Detection

1 code implementation CVPR 2021 Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Jinqiao Wang, Ming Tang

To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies.

object-detection Object Detection

The distance between the weights of the neural network is meaningful

no code implementations31 Jan 2021 Liqun Yang, Yijun Yang, Yao Wang, Zhenyu Yang, Wei Zeng

In the application of neural networks, we need to select a suitable model based on the problem complexity and the dataset scale.

Modeling Spatial Nonstationarity via Deformable Convolutions for Deep Traffic Flow Prediction

no code implementations8 Jan 2021 Wei Zeng, Chengqiao Lin, Kang Liu, Juncong Lin, Anthony K. H. Tung

Furthermore, to better fit with convolutions, we suggest to first aggregate traffic flows according to pre-conceived regions or self-organized regions based on traffic flows, then dispose to sequentially organized raster images for network input.

Traffic Prediction

Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos

1 code implementation13 Aug 2020 Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai

However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.

Action Assessment Action Quality Assessment

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics

no code implementations30 Jul 2020 Wei Zeng, Chengqiao Lin, Juncong Lin, Jincheng Jiang, Jiazhi Xia, Cagatay Turkay, Wei Chen

Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks.

Traffic Prediction

Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient

no code implementations25 Jul 2020 Haonan Jia, Xiao Zhang, Jun Xu, Wei Zeng, Hao Jiang, Xiaohui Yan, Ji-Rong Wen

Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency.

Q-Learning reinforcement-learning +1

Prediction of Physical Load Level by Machine Learning Analysis of Heart Activity after Exercises

no code implementations20 Dec 2019 Peng Gang, Wei Zeng, Yuri Gordienko, Oleksandr Rokovyi, Oleg Alienin, Sergii Stirenko

The classification problem was to predict the known level of the in-exercise loads (in three categories by calories) by the heart rate activity features measured during the short period of time (1 minute only) after training, i. e by features of the post-exercise load.

BIG-bench Machine Learning

LassoNet: Deep Lasso-Selection of 3D Point Clouds

no code implementations31 Jul 2019 Zhutian Chen, Wei Zeng, Zhiguang Yang, Lingyun Yu, Chi-Wing Fu, Huamin Qu

A hierarchical network is trained using a dataset with over 30K lasso-selection records on two different point cloud data.

Human-Computer Interaction Graphics

Off-policy Learning for Multiple Loggers

no code implementations23 Jul 2019 Li He, Long Xia, Wei Zeng, Zhi-Ming Ma, Yihong Zhao, Dawei Yin

To make full use of such historical data, learning policies from multiple loggers becomes necessary.

A collaborative filtering model with heterogeneous neural networks for recommender systems

no code implementations27 May 2019 Ge Fan, Wei Zeng, Shan Sun, Biao Geng, Weiyi Wang, Weibo Liu

One advantage of deep neural network is that the performance of the algorithm can be easily enhanced by augmenting the depth of the neural network.

Collaborative Filtering Recommendation Systems +2

Design Rule Violation Hotspot Prediction Based on Neural Network Ensembles

no code implementations9 Nov 2018 Wei Zeng, Azadeh Davoodi, Yu Hen Hu

Design rule check is a critical step in the physical design of integrated circuits to ensure manufacturability.

Ensemble Learning Test

Open Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti

no code implementations31 Aug 2018 Nikita Gordienko, Peng Gang, Yuri Gordienko, Wei Zeng, Oleg Alienin, Oleksandr Rokovyi, Sergii Stirenko

A new image dataset of these carved Glagolitic and Cyrillic letters (CGCL) was assembled and pre-processed for recognition and prediction by machine learning methods.

BIG-bench Machine Learning Data Augmentation +1

Parallel Statistical and Machine Learning Methods for Estimation of Physical Load

no code implementations14 Aug 2018 Sergii Stirenko, Gang Peng, Wei Zeng, Yuri Gordienko, Oleg Alienin, Oleksandr Rokovyi, Nikita Gordienko

Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue .

BIG-bench Machine Learning

MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server

no code implementations22 Apr 2018 Guoxin Cui, Jun Xu, Wei Zeng, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations.

BIG-bench Machine Learning Quantization +2

Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentation

1 code implementation3 Mar 2018 Sergii Stirenko, Yuriy Kochura, Oleg Alienin, Oleksandr Rokovyi, Peng Gang, Wei Zeng, Yuri Gordienko

Lossless data augmentation of the segmented dataset leads to the lowest validation loss (without overfitting) and nearly the same accuracy (within the limits of standard deviation) in comparison to the original and other pre-processed datasets after lossy data augmentation.

Data Augmentation Segmentation

Dimensionality Reduction in Deep Learning for Chest X-Ray Analysis of Lung Cancer

no code implementations19 Jan 2018 Yu. Gordienko, Yu. Kochura, O. Alienin, O. Rokovyi, S. Stirenko, Peng Gang, Jiang Hui, Wei Zeng

Efficiency of some dimensionality reduction techniques, like lung segmentation, bone shadow exclusion, and t-distributed stochastic neighbor embedding (t-SNE) for exclusion of outliers, is estimated for analysis of chest X-ray (CXR) 2D images by deep learning approach to help radiologists identify marks of lung cancer in CXR.

Dimensionality Reduction Segmentation

Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer

no code implementations20 Dec 2017 Yu. Gordienko, Peng Gang, Jiang Hui, Wei Zeng, Yu. Kochura, O. Alienin, O. Rokovyi, S. Stirenko

The recent progress of computing, machine learning, and especially deep learning, for image recognition brings a meaningful effect for automatic detection of various diseases from chest X-ray images (CXRs).


Surface Registration by Optimization in Constrained Diffeomorphism Space

no code implementations CVPR 2014 Wei Zeng, Lok Ming Lui, Xianfeng GU

The physically plausible constraints, in terms of feature landmarks and deformation types, define subspaces in the Beltrami coefficient space.

Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration

no code implementations CVPR 2013 Rui Shi, Wei Zeng, Zhengyu Su, Hanna Damasio, Zhonglin Lu, Yalin Wang, Shing-Tung Yau, Xianfeng GU

This work conquer this problem by changing the Riemannian metric on the target surface to a hyperbolic metric, so that the harmonic mapping is guaranteed to be a diffeomorphism under landmark constraints.

Area Preserving Brain Mapping

no code implementations CVPR 2013 Zhengyu Su, Wei Zeng, Rui Shi, Yalin Wang, Jian Sun, Xianfeng GU

Experimental results on caudate nucleus surface mapping and cortical surface mapping demonstrate the efficacy and efficiency of the proposed method.

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