Search Results for author: Zhenhua Wang

Found 36 papers, 7 papers with code

Exploring the Law of Numbers: Evidence from China's Real Estate

no code implementations11 Sep 2023 Fuqian Zhang, Zhenhua Wang

The renowned proverb, Numbers do not lie, underscores the reliability and insight that lie beneath numbers, a concept of undisputed importance, especially in economics and finance etc.

Exploring the law of text geographic information

no code implementations1 Sep 2023 Zhenhua Wang, Daiyu Zhang, Ming Ren, Guang Xu

Textual geographic information is indispensable and heavily relied upon in practical applications.

Will Sentiment Analysis Need Subculture? A New Data Augmentation Approach

no code implementations1 Sep 2023 Zhenhua Wang, Simin He, Guang Xu, Ming Ren

The renowned proverb that "The pen is mightier than the sword" underscores the formidable influence wielded by text expressions in shaping sentiments.

Data Augmentation Sentiment Analysis

Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models

no code implementations16 Aug 2023 Zhenhua Wang, Wei Xie, Kai Chen, Baosheng Wang, Zhiwen Gui, Enze Wang

Inspired by the attack that penetrates traditional firewalls through reverse tunnels, we introduce a "self-deception" attack that can bypass the semantic firewall by inducing LLM to generate prompts that facilitate jailbreak.

Human-to-Human Interaction Detection

no code implementations2 Jul 2023 Zhenhua Wang, Kaining Ying, Jiajun Meng, Jifeng Ning

First, based on the popular AVA dataset created for action detection, we establish a new HID benchmark, termed AVA-Interaction (AVA-I), by adding annotations on interactive relations in a frame-by-frame manner.

Action Detection Human Interaction Recognition

3D Object Aided Self-Supervised Monocular Depth Estimation

no code implementations4 Dec 2022 Songlin Wei, Guodong Chen, Wenzheng Chi, Zhenhua Wang, Lining Sun

Specifically, we first detect 3D objects in the images and build the per-pixel correspondence of the dynamic pixels with the detected object pose while leaving the static pixels corresponding to the rigid background to be modeled with camera motion.

Autonomous Driving Monocular 3D Object Detection +4

A new hazard event classification model via deep learning and multifractal

no code implementations12 Sep 2022 Zhenhua Wang, Bin Wang, Ming Ren, Dong Gao

Then, a new multifractal analysis method termed HmF-DFA is proposed to win HaE fractal series by analyzing HaE time series.

Classification Time Series +1

Yes, DLGM! A novel hierarchical model for hazard classification

no code implementations10 Sep 2022 Zhenhua Wang, Ming Ren, Dong Gao, Bin Wang

In this paper, we propose a novel model termed DLGM via deep learning for hazard classification.

Classification Time Series +1

A Zipf's Law-based Text Generation Approach for Addressing Imbalance in Entity Extraction

no code implementations25 May 2022 Zhenhua Wang, Ming Ren, Dong Gao, Zhuang Li

The Zipf's Law emerges as a well-suited adoption, and to transition from words to entities, words within the documents are classified as common and rare ones.

Text Generation

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation

3 code implementations21 Apr 2022 Xiaoyan Li, Gang Zhang, Hongyu Pan, Zhenhua Wang

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms.

Autonomous Driving LIDAR Semantic Segmentation +2

ISDA: Position-Aware Instance Segmentation with Deformable Attention

1 code implementation23 Feb 2022 Kaining Ying, Zhenhua Wang, Cong Bai, Pengfei Zhou

Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing.

Instance Segmentation Position +2

A novel knowledge graph development for industry design: A case study on indirect coal liquefaction process

no code implementations27 Nov 2021 Zhenhua Wang, Beike Zhang, Dong Gao

In order to reuse and unlock the value of ISK and optimize HAZOP, we have developed a novel knowledge graph for industrial safety (ISKG) with HAZOP as the carrier through bridging data science and engineering design.

Question Answering

A New Multifractal-based Deep Learning Model for Text Mining

no code implementations27 Nov 2021 Zhenhua Wang, Ming Ren, Dong Gao

In this world full of uncertainty, where the fabric of existence weaves patterns of complexity, multifractal emerges as beacons of insight, illuminating them.

Chinese Named Entity Recognition named-entity-recognition +1

Why KDAC? A general activation function for knowledge discovery

no code implementations27 Nov 2021 Zhenhua Wang, Dong Gao, Haozhe Liu, Fanglin Liu

We hope that KDAC can be exploited as a promising activation function to devote itself to the construction of knowledge.

named-entity-recognition Named Entity Recognition +1

Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison

1 code implementation14 Mar 2021 Zhenhua Wang, Olanrewaju Akande, Jason Poulos, Fan Li

We conduct extensive simulation studies based on a subsample of the American Community Survey to compare the repeated sampling properties of four machine learning based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation networks, and multiple imputation using denoising autoencoders.

Denoising Imputation

Operator means in JB-algebras

no code implementations24 Dec 2020 Shuzhou Wang, Zhenhua Wang

In this paper, the notion of operator means in the setting of JB-algebras is introduced and their properties are studied.

Functional Analysis Mathematical Physics Mathematical Physics 47A63, 47A64, 46H70, 47A60(Primary), 17C65, 81R15, 81P45, 94C99(Secondary)

Accurate Object Association and Pose Updating for Semantic SLAM

no code implementations21 Dec 2020 Kaiqi Chen, Jialing Liu, Jianhua Zhang, Zhenhua Wang

The key to solving this problem is to correctly associate multiple object measurements of one object landmark, and refine the pose of object landmark.

Multiple Object Tracking Object +1

Graph Attention Tracking

no code implementations CVPR 2021 Dongyan Guo, Yanyan Shao, Ying Cui, Zhenhua Wang, Liyan Zhang, Chunhua Shen

We propose to establish part-to-part correspondence between the target and the search region with a complete bipartite graph, and apply the graph attention mechanism to propagate target information from the template feature to the search feature.

Graph Attention Object Tracking +1

Consistency-Aware Graph Network for Human Interaction Understanding

1 code implementation ICCV 2021 Zhenhua Wang, Jiajun Meng, Dongyan Guo, Jianhua Zhang, Javen Qinfeng Shi, ShengYong Chen

Compared with the progress made on human activity classification, much less success has been achieved on human interaction understanding (HIU).

3D human pose and shape estimation

Optimal Equilibria for Multi-dimensional Time-inconsistent Stopping Problems

no code implementations1 Jun 2020 Yu-Jui Huang, Zhenhua Wang

We study an optimal stopping problem under non-exponential discounting, where the state process is a multi-dimensional continuous strong Markov process.

SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking

2 code implementations CVPR 2020 Dongyan Guo, Jun Wang, Ying Cui, Zhenhua Wang, Sheng-Yong Chen

The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction.

Classification General Classification +3

New Convex Relaxations for MRF Inference With Unknown Graphs

no code implementations ICCV 2019 Zhenhua Wang, Tong Liu, Qinfeng Shi, M. Pawan Kumar, Jianhua Zhang

The CCCP algorithm is initialized by solving a convex QP relaxation of the problem, which is obtained by modifying the diagonal of the matrix that specifies the non-convex QP relaxation.

Human Activity Recognition

End-to-end feature fusion siamese network for adaptive visual tracking

no code implementations4 Feb 2019 Dongyan Guo, Jun Wang, Weixuan Zhao, Ying Cui, Zhenhua Wang, Sheng-Yong Chen

Both features and the channel weights are utilized in a template generation layer to generate a discriminative template.

Visual Tracking

DCI: Discriminative and Contrast Invertible Descriptor

no code implementations31 Dec 2018 Zhenwei Miao, Kim-Hui Yap, Xudong Jiang, Subbhuraam Sinduja, Zhenhua Wang

In this paper, we proposed a Discriminative and Contrast Invertible (DCI) local feature descriptor.

Object Object Recognition +1

Neuron-level Selective Context Aggregation for Scene Segmentation

no code implementations22 Nov 2017 Zhenhua Wang, Fanglin Gu, Dani Lischinski, Daniel Cohen-Or, Changhe Tu, Baoquan Chen

Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation.

Scene Segmentation Segmentation

Recurrent Attentional Networks for Saliency Detection

no code implementations CVPR 2016 Jason Kuen, Zhenhua Wang, Gang Wang

Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection.

Saliency Detection

Recent Advances in Convolutional Neural Networks

no code implementations22 Dec 2015 Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Li Wang, Gang Wang, Jianfei Cai, Tsuhan Chen

In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.

speech-recognition Speech Recognition

Learning Fine-grained Features via a CNN Tree for Large-scale Classification

no code implementations14 Nov 2015 Zhenhua Wang, Xingxing Wang, Gang Wang

The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes.

General Classification Image Classification

Affine Subspace Representation for Feature Description

no code implementations18 Jul 2014 Zhenhua Wang, Bin Fan, Fuchao Wu

This paper proposes a novel Affine Subspace Representation (ASR) descriptor to deal with affine distortions induced by viewpoint changes.

A Hybrid Loss for Multiclass and Structured Prediction

no code implementations9 Feb 2014 Qinfeng Shi, Mark Reid, Tiberio Caetano, Anton Van Den Hengel, Zhenhua Wang

We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs).

Action Recognition Structured Prediction +1

Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs

no code implementations CVPR 2013 Zhenhua Wang, Qinfeng Shi, Chunhua Shen, Anton Van Den Hengel

Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty.

Human Activity Recognition

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