Selected Publications

• Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything
  European Conference on Computer Vision (ECCV), Malmö, Sweden, Sep. 2026, pp.xxx-xxx.
  [Code,Coming soon] [Poster, Coming soon] [Slides, Coming soon] [Video Presentation, Coming soon] [CCF-B]

• AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
  AAAI Conference on Artificial Intelligence (AAAI), Singapore, Jan. 2026, pp.4095–4103.
  [Code] [Poster] [Slides] [CCF-A]

• MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
  Neural Information Processing Systems. (NeurIPS), Vancouver, Canada, Dec. 2024, pp.39812-39836.
  [Code] [Poster] [Slides] [CCF-A]

• Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
  European Conference on Computer Vision (ECCV), Milan, Italy, Sep. 2024, pp.454-470.
  [Code] [Poster] [Slides] [Video Presentation] [CCF-B]

• Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
  European Conference on Computer Vision (ECCV), Milan, Italy, Sep. 2024, pp.210-226.
  [Code] [Poster] [CCF-B]

• Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection
  AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, Feb 2024, pp.7096-7104.
  [Code, Coming soon] [CCF-A]
  

• Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
  Neural Information Processing Systems (NeurIPS), New Orleans, USA, Dec 2022, pp.18640-18652.
  [Code] [Project] [Slides] [FSOD-Leaderboard] [Video Presentation] [CCF-A]

• Age Estimation Using Expectation of Label Distribution Learning
  Int'l Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, Jul 2018, pp.712-718.
  [Code] [Project] [CCF-A]

• Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era
  Pattern Recognition (PR), 113354, 2026.
  [Dataset] [SCI-1, IF:9.1]

• Dual-Masked and Discriminative Reconstruction for Unified Vision Anomaly Detection
  IEEE Transactions on Image Processing (IEEE TIP), 35:4701-4712, 2026.
  [Code] [SCI-1, IF:15.3]

• CSTrans: Correlation-guided Self-Activation Transformer for Counting Everything
  Pattern Recognition (PR), 110556, 2024.
  [Code] [SCI-1, IF:9.1]

• How to Reduce Change Detection to Semantic Segmentation
  Pattern Recognition (PR), 109384, 2023.
  [Code] [SCI-1, IF:9.1]

• Cross-Modal Alternating Learning with Task-Aware Representations for Continual Learning
  IEEE Transactions on Multimedia (IEEE TMM), 26:5911-5924, 2023.
  [Code] [SCI-1, IF:9.9]

• APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
  IEEE Transactions on Multimedia (IEEE TMM), 25:4361-4373, 2022.
  [Code] [SCI-1, IF:9.9]

• Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
  IEEE Transactions on Image Processing (IEEE TIP), 20:5920-5932, 2021.
  [Code] [SCI-1, IF:15.3]

• Deep Label Distribution Learning with Label Ambiguity
  IEEE Transactions on Image Processing (IEEE TIP), 26(6):2825-2838, 2017.
  [Code] [Project] [SCI-1, IF:15.3] [ESI Highly Cited Paper, Top 1%]