Shiming Chen   陈使明

Postdoctoral Research Fellow

Email: gchenshiming at gmail dot com

Shiming Chen

Short Bios

I received my Ph.D. degree at Huazhong University of Science and Technology in Dec. 2022, advised by Prof. Xinge You and worked closely Prof. Ling Shao. My current research interests span computer vision and machine learning with a series of topics, such as zero-shot learning, generative modeling and learning, and visual-and-language learning.

News

Researches

A key challenge of artificial intelligence is to generalize machine learning models from seen data to unseen scenarios. Zero-shot learning (ZSL) is a typical research topic targeting this goal. ZSL aims to classify the images of unseen classes by constructing a mapping relationship between the semantic and visual domains. Although ZSL has achieved significant progress, there have a numbers of essential challenges. Recently, large-scale VLM-based ZSL method is popular, e.g., CLIP, it is an extension of the classical ZSL.

Dr. Shiming Chen has been focusing on tackling bottleneck challenges to promote ZSL (especially for the classical ZSL), covering fundamental questions of How to enhance the visual features by alleviating the cross-dataset bias between pre-train dataset and ZSL benchmarks? How to discover the intrinsic semantic knowledge by alleviating the visual-semantic domain shift problem? How to align the visual and semantic features in a common space by reducing the discrepancy between the heterogeneous visual-semantic representations? Specifically, his three representatives research projects are:

1. Developing the visual feature enhancement algorithms to tackle the challenge of cross-dataset bias in ZSL. As for the embedding-based ZSL, a graph-guided dual attention network is introduced to fuse the local visual features and explicit global visual features to enhance visual features. As for the generative ZSL, several feature refinement learning methods are proposed to enhance the visual features and encourage the generator to synthesize realistic visual features for unseen classes. The papers of this project have been published in ICCV'21, IJCAI'22, IEEE TNNLS'22, etc.

2. Developing the effective ZSL algorithms to tackle the visual-semantic domain shift problem. As for the embedding-based ZSL, a attribute-guided Transformer network and mutually semantic distillation network are proposed to learn the intrinsic semantic knowledge, enriching the visual features with semantic information to enable desirable semantic knowledge transfer from seen calsses to unseen ones. As for the generative ZSL, dynamic semantic prototype learning is proposed to refine the pre-defined semantic prototypes under the guidance of visual signal, aligning the empirical and actual semantic prototypes for synthesizing accurate visual features. The papers of this project have been published in CVPR'22, AAAI'22, IEEE TPAMI'22, IEEE TEC'23, ICML'23 , CVPR'24 , etc.

3. Developing the semantic-visual adaptation framework for visual-semantic alignment. Different to existing one-step adaptation method that on alignment the feature distributions between visual and semantic domains, this method utilizes a hierarchical adaptation to learn an intrinsic common space for semantic and visual feature representations by adopting sequential structure adaptation and distribution adaptation. The papers of this project have been published in NeurIPS'21, CVPR'24 .



Latest Publications (Google Scholar)

(*:Co-First Author; #:Corresponding Author)

Survey Papers

Few-shot object detection: Research advances and challenges. [PDF] [arXiv]

Zhimeng Xin, Shiming Chen, Tianxu Wu, Yuanjie Shao, Weiping Ding, Xinge You.

Information Fusion, 108, 102307 (2024). (SCI, IF=18.6)

Conference Papers

Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning. [PDF] [arXiv] [Code]

Shiming Chen, Wenjin Hou, Salman Khan, Fahad Shahbaz Khan.

IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2024. (CCF Rank-A)

Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning. [PDF] [arXiv] [Code]

Wenjin Hou, Shiming Chen#, Shuhuang Chen, Ziming Hong, Yan Wang, Xuetao Feng, Salman Khan, Fahad Shahbaz Khan, Xinge You.

IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2024. (CCF Rank-A)

Evolving Semantic Prototype Improves Generative Zero-Shot Learning. [PDF] [arXiv]

Shiming Chen, Wenjin Hou, Ziming Hong, Xiaohan Ding, Yibing Song, Xinge You, Tongliang Liu, Kun Zhang.

The Fortieth International Conference on Machine Learning ( ICML ), 2023. (CCF Rank-A)

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning. [PDF] [arXiv] [Code]

Shiming Chen, Ziming Hong, Guo-Sen Xie, Wenhan Yang, Qinmu Peng, Kai Wang, Jian Zhao, Xinge You.

IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2022: 7612-7621. (CCF Rank-A)

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning. [PDF] [arXiv] [Code]

Shiming Chen, Guo-Sen Xie, Qinmu Peng, Yang Liu, Baigui Sun, Hao Li, Xinge You, Ling Shao.

Annual Conference on Neural Information Processing Systems ( NeurIPS ), 2021: 16622-16634. (CCF Rank-A)

FREE: Feature Refinement for Generalized Zero-shot Learning. [PDF] [arXiv] [Code]

Shiming Chen, Wenjie Wang, Beihao Xia, Qinmu Peng, Xinge You, Feng Zheng, Ling Shao.

IEEE International Conference on Computer Vision ( ICCV ), 2021: 1106-1112. (CCF Rank-A)

TransZero: Attribute-guided Transformer for Zero-Shot Learning. [PDF] [arXiv] [Code]

Shiming Chen*, Ziming Hong*, Yang Liu, Guo-Sen Xie, Baigui Sun, Hao Li, Qinmu Peng, Ke Lu, Xinge You.

Thirty-Sixth AAAI Conference on Artificial Intelligence ( AAAI ), 2022: 330-338. (CCF Rank-A)

Semantic Compression Embedding for Generative Zero-Shot Learning. [PDF] [Code]

Ziming Hong*, Shiming Chen*#, Guo-Sen Xie, Wenhan Yang, Jian Zhao, Yuanjie Shao, Qinmu Peng, Xinge You

The 31th International Joint Conference on Artificial Intelligence ( IJCAI ), 2022: 956-963. (CCF Rank-A)

Journal Papers

TransZero++: Cross Attribute-guided Transformer for Zero-Shot Learning. [Project Page] [PDF] [arXiv] [Code]

Shiming Chen, Ziming Hong, Wenjin Hou, Guo-Sen Xie, Yibing Song, Jian Zhao, Xinge You, Shuicheng Yan, Ling Shao.

IEEE Transactions on Pattern Analysis and Machine Intelligence ( TPAMI ), 45(11):12844-12861, 2023. (SCI, IF=24.314, CCF Rank-A)

ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection. [PDF] [arXiv]

Zhimeng Xin, Tianxu Wu, Shiming Chen#, Yixiong Zou, Ling Shao, Xinge You.

IEEE Transactions on Image Processing ( TIP ), 33:5564-5576, 2024. (SCI, IF=10.6, CCF Rank-A)

Rethinking attribute localization for zero-shot learning. [PDF]

Shuhuang Chen, Shiming Chen#, Guo-sen Xie, Xiangbo Shu, Xinge You, Xuelong Li.

SCIENCE CHINA Information Sciences, 67, 172103 (2024). (SCI, IF=8.8, CCF Rank-A)

EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning. [PDF] [arXiv] [Code]

Shiming Chen, Shuhuang Chen, Wenjin Hou,Weiping Ding, Xinge You.

IEEE Transactions on Evolutionary Computation ( TEC ), 28(3):582-596, 2024. (SCI, IF=14.3, CCF Rank-B)

GNDAN: Graph Navigated Dual Attention Network for Zero-Shot Learning. [PDF] [Code]

Shiming Chen, Ziming Hong, Guo-Sen Xie, Xinge You, Weiping Ding and Ling Shao.

IEEE Transactions on Neural Networks and Learning Systems ( TNNLS), 35(4):4516-4529, 2024. (SCI, IF=14.255, CCF Rank-B)

CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network. [PDF] [arXiv] [Code]

Shiming Chen, Wenjie Wang, Beihao Xia, Xinge You, Qinmu Peng, Zehong Cao, Weiping Ding.

IEEE Transactions on Evolutionary Computation ( TEC ), 25:986-1000, 2021. (SCI, IF=14.3, CCF Rank-B)

Kernelized Similarity Learning and Embedding for Dynamic Texture Synthesis. [Code] [arXiv]

Shiming Chen, Peng Zhang, Guo-sen Xie, Zehong Cao, Qinmu Peng, Wei Yuan, Xinge You.

IEEE Transactions on Systems, Man and Cybernetics: Systems ( TSMCA), 53(2):824-837, 2023. (SCI, IF=11.471)

Awards

  • 2022.08, Huawei Academic Star.
  • 2022.10, China National Scholarship.
  • Work Experience

    Professional Services

    Area Chair: PRCV'23, VALSE.
    Journal Reviewers: TPAMI, IJCV, TIP, TNNLS, TEC, TCYB, TSMCA, TITS, TII, TMM, TASE, TIV, etc.
    Conference PC/Reviewers: ICLR'23-24, NeurIPS'23, CVPR'22-24, ICCV'21-23, ECCV'22-24, AAAI'22-24, IJCAI'21-23, ACM MM'21.

    Invited Talks

    • School of Information Science and Technology, University of Science and Technology of China
      Jun. 2023

      Title: Zero-Shot Learning in Vision
    • Alibaba DAMO Academic
      Apr. 2023

      Title: Semantic-Guided Zero-Shot Learning
    • Department of Mathematics and Statistics, Huazhong Agricultural Univeristy
      Apr. 2023

      Title: Attribute Based Zero-Shot Learning
    • School of Computer Science and Technology, Guizhou University
      Apr. 2023

      Title: Semantic-Guided Zero-Shot Learning
    • National Key Laboratory of Science and Technology on Multispectral Information Processing
      Mar. 2023

      Title: Deep Feature Representations Based Zero-Shot Learning
    • IEEE International Conference on Digital Twins and Parallel Intelligence
      Nov. 2022

      Title: Mutually Semantic Distillation Network for Zero-Shot Learning
    • Huawei (Shanghai)
      Aug. 2022

      Title: Deep Feature Representations Based Zero-Shot Image Classification
    • Zhidongxi (AI New Youth)
      Aug. 2022

      Title: MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning
    • VALSE
      Jun. 2022

      Title: Mutually Semantic Distillation Network for Zero-Shot Learning
    • AI Drive
      Jun. 2022

      Title: Mutually Semantic Distillation Network for Zero-Shot Learning
    • AI TIME
      Jun. 2022

      Title: Attribute-guided Transformer for Zero-Shot Learning
    • Extreme Mart
      Feb. 2022

      Title: Research on Key Technology for Zero-shot Learning
    • AI TIME
      Feb. 2022

      Title: 基于层次适应的零样本学习
    • CVTE
      Dec. 2021

      Title: Recent Advances in Zero-Shot Learning
    • Tencent AI Lab
      Dec. 2021

      Title: The Frontiers in Zero-Shot Learning
    • Alibaba DAMO Academic
      Aug. 2021

      Title: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning