Search Results for author: Huibing Wang

Found 32 papers, 6 papers with code

Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance

no code implementations16 May 2024 Huibing Wang, Mingze Yao, Yawei Chen, Yunqiu Xu, Haipeng Liu, Wei Jia, Xianping Fu, Yang Wang

Moreover, to preserve the consistency information among multiple views, MIMB implements a biconsistency guidance strategy with reverse regularization of the consensus representation and proposes a manifold embedding measure for exploring the hidden structure of the recovered data.

Clustering Incomplete multi-view clustering +1

Fast One-Stage Unsupervised Domain Adaptive Person Search

1 code implementation5 May 2024 Tianxiang Cui, Huibing Wang, Jinjia Peng, Ruoxi Deng, Xianping Fu, Yang Wang

Unsupervised person search aims to localize a particular target person from a gallery set of scene images without annotations, which is extremely challenging due to the unexpected variations of the unlabeled domains.

Clustering Person Search

Scene-Adaptive Person Search via Bilateral Modulations

no code implementations5 May 2024 Yimin Jiang, Huibing Wang, Jinjia Peng, Xianping Fu, Yang Wang

In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware.

Person Search

Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videos

1 code implementation8 Aug 2023 Huibing Wang, Tianxiang Cui, Mingze Yao, Huijuan Pang, Yushan Du

In order to facilitate the feature learning of the GAN-based Scene Synthesis model, we adopt an online learning strategy that collaboratively learns the synthesized images and original images.

Person Search

Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering

no code implementations6 Jan 2023 Huibing Wang, Mingze Yao, Guangqi Jiang, Zetian Mi, Xianping Fu

To address the above issues, we propose a hashing algorithm based on auto-encoders for multi-view binary clustering, which dynamically learns affinity graphs with low-rank constraints and adopts collaboratively learning between auto-encoders and affinity graphs to learn a unified binary code, called Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering (GCAE).

Clustering Quantization

Unsupervised Vehicle Re-identification with Progressive Adaptation

no code implementations20 Jun 2020 Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang

For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.

Unsupervised Vehicle Re-Identification Vehicle Re-Identification

Multi-view Low-rank Preserving Embedding: A Novel Method for Multi-view Representation

no code implementations14 Jun 2020 Xiangzhu Meng, Lin Feng, Huibing Wang

Unlike existing methods with additive parameters, the proposed method could automatically allocate a suitable weight for each view in multi-view information fusion.

MULTI-VIEW LEARNING Representation Learning

Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification

no code implementations16 Mar 2020 Huibing Wang, Jinjia Peng, Guangqi Jiang, Fengqiang Xu, Xianping Fu

In TCPM, triplet-center loss is introduced to ensure each part of vehicle features extracted has intra-class consistency and inter-class separability.

Dictionary Learning Vehicle Re-Identification

Attribute-guided Feature Learning Network for Vehicle Re-identification

no code implementations12 Jan 2020 Huibing Wang, Jinjia Peng, Dongyan Chen, Guangqi Jiang, Tongtong Zhao, Xianping Fu

Specially, an attribute-guided module is proposed in AGNet to generate the attribute mask which could inversely guide to select discriminative features for category classification.

Attribute Vehicle Re-Identification

Eliminating cross-camera bias for vehicle re-identification

no code implementations21 Dec 2019 Jinjia Peng, Guangqi Jiang, Dongyan Chen, Tongtong Zhao, Huibing Wang, Xianping Fu

Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras.

Vehicle Re-Identification

Graph-based Multi-view Binary Learning for Image Clustering

no code implementations11 Dec 2019 Guangqi Jiang, Huibing Wang, Jinjia Peng, Dongyan Chen, Xianping Fu

To address these problems, we propose a novel binary code algorithm for clustering, which adopts graph embedding to preserve the original data structure, called (Graph-based Multi-view Binary Learning) GMBL in this paper.

Clustering Graph Embedding +1

Kernelized Multiview Subspace Analysis by Self-weighted Learning

no code implementations23 Nov 2019 Huibing Wang, Yang Wang, Zhao Zhang, Xianping Fu, Zhuo Li, Mingliang Xu, Meng Wang

With the popularity of multimedia technology, information is always represented or transmitted from multiple views.

Dimensionality Reduction Image Retrieval +1

The Similarity-Consensus Regularized Multi-view Learning for Dimension Reduction

no code implementations15 Nov 2019 Xiangzhu Meng, Huibing Wang, Lin Feng

Two schemes based on pairwise-consensus and centroid-consensus are separately proposed to force multiple views to learn from each other and then an iterative alternating strategy is developed to obtain the optimal solution.

Dimensionality Reduction MULTI-VIEW LEARNING

A Multi-view Dimensionality Reduction Algorithm Based on Smooth Representation Model

no code implementations10 Oct 2019 Haohao Li, Huibing Wang

The proposed method aims to find a subspace for the high-dimensional data, in which the smooth reconstructive weights are preserved as much as possible.

Dimensionality Reduction

Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation

no code implementations10 Jul 2019 Yuxiao Yan, Yang Yan, Jinjia Peng, Huibing Wang, Xianping Fu

Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images.

Gaze Estimation Style Transfer

Multi-view Locality Low-rank Embedding for Dimension Reduction

no code implementations20 May 2019 Lin Feng, Xiangzhu Meng, Huibing Wang

Even though most of them can achieve satisfactory performance in some certain situations, they fail to fully consider the information from multiple views which are highly relevant but sometimes look different from each other.

Dimensionality Reduction

A fast online cascaded regression algorithm for face alignment

no code implementations10 May 2019 Lin Feng, Caifeng Liu, Shenglan Liu, Huibing Wang

Traditional face alignment based on machine learning usually tracks the localizations of facial landmarks employing a static model trained offline where all of the training data is available in advance.

Face Alignment Incremental Learning +1

Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification

no code implementations30 Apr 2019 Jinjia Peng, Huibing Wang, Xianping Fu

To address this problem, this paper proposes a domain adaptation framework for vehicle reID (DAVR), which narrows the cross-domain bias by fully exploiting the labeled data from the source domain to adapt the target domain.

Domain Adaptation Image-to-Image Translation +1

Co-regularized Multi-view Sparse Reconstruction Embedding for Dimension Reduction

no code implementations1 Apr 2019 Huibing Wang, Jinjia Peng, Xianping Fu

However, facing with features from multiple views, it's difficult for most dimension reduction methods to fully comprehended multi-view features and integrate compatible and complementary information from these features to construct low-dimensional subspace directly.

Dimensionality Reduction Document Classification +3

Mask-guided Style Transfer Network for Purifying Real Images

no code implementations19 Mar 2019 Tongtong Zhao, Yuxiao Yan, Jinjia Peng, Huibing Wang, Xianping Fu

To solve this problem, the previous method learned a model to improve the realism of the synthetic images.

Style Transfer

Self-Weighted Multiview Metric Learning by Maximizing the Cross Correlations

no code implementations19 Mar 2019 Huibing Wang, Jinjia Peng, Xianping Fu

With the development of multimedia time, one sample can always be described from multiple views which contain compatible and complementary information.

Face Recognition Image Retrieval +2

Bottom-up Broadcast Neural Network For Music Genre Classification

1 code implementation24 Jan 2019 Caifeng Liu, Lin Feng, Guochao Liu, Huibing Wang, Shenglan Liu

Music genre recognition based on visual representation has been successfully explored over the last years.

Classification Decision Making +4

Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval

no code implementations10 Jan 2019 Huibing Wang, Haohao Li, Xianping Fu

To address these issue, a novel multi-feature distance metric learning method for non-rigid 3D shape retrieval is presented in this study, which can make full use of the complimentary geometric information from multiple shape features by utilizing the KL-divergences.

3D Shape Classification 3D Shape Retrieval +2

Auto-weighted Mutli-view Sparse Reconstructive Embedding

no code implementations5 Jan 2019 Huibing Wang, Haohao Li, Xianping Fu

Therefore, it is essential to fully exploit the complementary information embedded in multiple views to enhance the performances of many tasks.

Dimensionality Reduction

Learning to predict crisp boundaries

1 code implementation ECCV 2018 Ruoxi Deng, Chunhua Shen, Shengjun Liu, Huibing Wang, Xinru Liu

Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries.

Boundary Detection Edge Detection

Robust Tracking via Weighted Online Extreme Learning Machine

no code implementations26 Jul 2018 Jing Zhang, Huibing Wang, Yong-Gong Ren

Therefore, our tracking method can fully learn both of the target object and background information to enhance the tracking performance, and it is evaluated in 20 challenge image sequences with different attributes including illumination, occlusion, deformation, etc., which achieves better performance than several state-of-the-art methods in terms of effectiveness and robustness.

Classification General Classification +2

Multi-view Reconstructive Preserving Embedding for Dimension Reduction

no code implementations25 Jul 2018 Huibing Wang, Lin Feng, Adong Kong, Bo Jin

With the development of feature extraction technique, one sample always can be represented by multiple features which locate in high-dimensional space.

Dimensionality Reduction Document Classification +3

Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition

1 code implementation4 Apr 2017 Qichang Hu, Huibing Wang, Teng Li, Chunhua Shen

By applying our method to several fine-grained car recognition data sets, we demonstrate that the proposed method can achieve better performance than recent approaches in the literature.

Fine-Grained Image Classification

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