Hui Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hui Chen has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jingjing Jiang
Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University
3 shared publications - Nanning Zheng
Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China
3 shared publications Nanning Zheng
2 shared publicationsYongqiang Ma
2 shared publications- Bir Bhanu
Department of Electrical and Computer Engineering, University of California, Riverside, CA, USA
1 shared publication - Haitao Wang
Nanjing Audit Univ, Jinshen Coll, Nanjing 210023, Peoples R China
1 shared publication
Latest Publications
- 17 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 639
Exploring inter- and intra-modal relations in compositional zero-shot learning
- 17 April 2025
- Published by Elsevier in Neurocomputing
- Vol. 639
Exploring inter- and intra-modal relations in compositional zero-shot learning
- 31 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
COSDA: Covariance regularized semantic data augmentation for self-supervised visual representation learning
- 31 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
COSDA: Covariance regularized semantic data augmentation for self-supervised visual representation learning
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (10) , 12022-12037
Learning to Infer Unseen Single-/ Multi-Attribute-Object Compositions With Graph Networks
Inferring the unseen attribute-object composition is critical to make machines learn to decompose and compose complex concepts like people. Most existing methods are limited to the composition recognition of single-attribute-object, and can hardly learn relations between the attributes and objects. In this paper, we propose an attribute-object semantic association graph model to learn the complex relations and enable knowledge transfer between primitives. With nodes representing attributes and objects, the graph can be constructed flexibly, which realizes both single- and multi-attribute-object composition recognition. In order to reduce mis-classifications of similar compositions (e.g., scratched screen and broken screen ), driven by the contrastive loss, the anchor image feature is pulled closer to the corresponding label feature and pushed away from other negative label features. Specifically, a novel balance loss is proposed to alleviate the domain bias, where a model prefers to predict seen compositions. In addition, we build a large-scale Multi-Attribute Dataset (MAD) with 116,099 images and 8,030 label categories for inferring unseen multi-attribute-object compositions. Along with MAD, we propose two novel metrics Hard and Soft to give a comprehensive evaluation in the multi-attribute setting. Experiments on MAD and two other single-attribute-object benchmarks (MIT-States and UT-Zappos50 K) demonstrate the effectiveness of our approach.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (10) , 12022-12037
Learning to Infer Unseen Single-/ Multi-Attribute-Object Compositions With Graph Networks
Inferring the unseen attribute-object composition is critical to make machines learn to decompose and compose complex concepts like people. Most existing methods are limited to the composition recognition of single-attribute-object, and can hardly learn relations between the attributes and objects. In this paper, we propose an attribute-object semantic association graph model to learn the complex relations and enable knowledge transfer between primitives. With nodes representing attributes and objects, the graph can be constructed flexibly, which realizes both single- and multi-attribute-object composition recognition. In order to reduce mis-classifications of similar compositions (e.g., scratched screen and broken screen ), driven by the contrastive loss, the anchor image feature is pulled closer to the corresponding label feature and pushed away from other negative label features. Specifically, a novel balance loss is proposed to alleviate the domain bias, where a model prefers to predict seen compositions. In addition, we build a large-scale Multi-Attribute Dataset (MAD) with 116,099 images and 8,030 label categories for inferring unseen multi-attribute-object compositions. Along with MAD, we propose two novel metrics Hard and Soft to give a comprehensive evaluation in the multi-attribute setting. Experiments on MAD and two other single-attribute-object benchmarks (MIT-States and UT-Zappos50 K) demonstrate the effectiveness of our approach.
- 10 June 2022
- Published by Springer Nature
- p. 316-327
Transformer-Based Zero-Shot Detection via Contrastive Learning
- 10 June 2022
- Published by Springer Nature
- p. 316-327
Transformer-Based Zero-Shot Detection via Contrastive Learning
- Open Access
Learning to Infer Unseen Attribute-Object Compositions
The composition recognition of unseen attribute-object is critical to make machines learn to decompose and compose complex concepts like people. Most of the existing methods are limited to the composition recognition of single-attribute-object, and can hardly distinguish the compositions with similar appearances. In this paper, a graph-based model is proposed that can flexibly recognize both single- and multi-attribute-object compositions. The model maps the visual features of images and the attribute-object category labels represented by word embedding vectors into a latent space. Then, according to the constraints of the attribute-object semantic association, distances are calculated between visual features and the corresponding label semantic features in the latent space. During the inference, the composition that is closest to the given image feature among all compositions is used as the reasoning result. In addition, we build a large-scale Multi-Attribute Dataset (MAD) with 116,099 images and 8,030 composition categories. Experiments on MAD and two other single-attribute-object benchmark datasets demonstrate the effectiveness of our approach.
Open AccessLearning to Infer Unseen Attribute-Object Compositions
The composition recognition of unseen attribute-object is critical to make machines learn to decompose and compose complex concepts like people. Most of the existing methods are limited to the composition recognition of single-attribute-object, and can hardly distinguish the compositions with similar appearances. In this paper, a graph-based model is proposed that can flexibly recognize both single- and multi-attribute-object compositions. The model maps the visual features of images and the attribute-object category labels represented by word embedding vectors into a latent space. Then, according to the constraints of the attribute-object semantic association, distances are calculated between visual features and the corresponding label semantic features in the latent space. During the inference, the composition that is closest to the given image feature among all compositions is used as the reasoning result. In addition, we build a large-scale Multi-Attribute Dataset (MAD) with 116,099 images and 8,030 composition categories. Experiments on MAD and two other single-attribute-object benchmark datasets demonstrate the effectiveness of our approach.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 663-665
Proficiency Testing Scheme of Conducted disturbance at mains terminals in 150kHz∼30MHz using Multi-items
The paper introduces a Proficiency Testing scheme of conducted disturbance at mains terminals in 150kHz∼30MHz using Multi-items method, compared with a single item Proficiency Testing scheme, test time and costs is greatly reduced, reliability is largely increased. 150 items which could generate comb signal with stable frequency and stable voltage in the frequency range of 150 kHz to 30MHz were developed. And the item could simulate the power supply, grounding and setup of the actual test sample. Mailed it to 101 participants in parallel to evaluates performance and identifies problems of participants.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 663-665
Proficiency Testing Scheme of Conducted disturbance at mains terminals in 150kHz∼30MHz using Multi-items
The paper introduces a Proficiency Testing scheme of conducted disturbance at mains terminals in 150kHz∼30MHz using Multi-items method, compared with a single item Proficiency Testing scheme, test time and costs is greatly reduced, reliability is largely increased. 150 items which could generate comb signal with stable frequency and stable voltage in the frequency range of 150 kHz to 30MHz were developed. And the item could simulate the power supply, grounding and setup of the actual test sample. Mailed it to 101 participants in parallel to evaluates performance and identifies problems of participants.
- 29 October 2015
- Published by Springer Nature
- p. 27-33
Classification and Comparative Analysis of Resource Management Methods in Ad Hoc Network
- 29 October 2015
- Published by Springer Nature
- p. 27-33
Classification and Comparative Analysis of Resource Management Methods in Ad Hoc Network
- 1 January 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10514651) , 574-577 Vol.3
Human ear detection from side face range images
Ear detection is an important part of an ear recognition system. In this paper, we address human ear detection from side face range images. We introduce a simple and an effective method to detect ears, which has two stages: offline model template building and on-line detection. The model template is represented by an averaged histogram of shape index. The on-line detection is a four-step process: step edge detection and thresholding, image dilation, connect-component labeling and template matching. Experimental results with real ear images are presented to demonstrate the effectiveness of our approach.
- 1 January 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10514651) , 574-577 Vol.3
Human ear detection from side face range images
Ear detection is an important part of an ear recognition system. In this paper, we address human ear detection from side face range images. We introduce a simple and an effective method to detect ears, which has two stages: offline model template building and on-line detection. The model template is represented by an averaged histogram of shape index. The on-line detection is a four-step process: step edge detection and thresholding, image dilation, connect-component labeling and template matching. Experimental results with real ear images are presented to demonstrate the effectiveness of our approach.