Submission Instructions

We welcome full paper submissions. The papers must be no longer than 9 pages in total: 7 pages for the body of the paper and 2 pages for references. Please submit at the following CMT website:
ADFM 2024 CMT submission website. 

The paper submissions must be in pdf format and use the IJCAI 2024 official templates. All submissions must be anonymous and conform to the IJCAI 2024 standards for double-blind review. The accepted papers will be posted on the workshop website and will not appear in the IJCAI 2024 proceedings. IJCAI 2024 workshop chairs enforce that at least one author of each accepted paper must travel to the IJCAI venue in person and present the paper, and that multiple submissions of the same paper to more IJCAI workshops are forbidden. Failure to comply with the aforesaid rules may cause the paper to be removed from the workshop program.  

Submission deadline: April 26 May 10, 2024 AOE Time  
Notification to authors: May 31, 2024
Camera ready deadline:  June 7 June 14, 2024 AOE Time

We invite the submission of original and high-quality research papers in the topics related to anomaly detection with foundation models. Each accepted paper will be presented as either an oral, spotlight, or poster presentation. 

Topics

The topics for ADFM 2024 include, but are not limited to:

• Foundations and principles of foundation models for anomaly detection.
• Innovative anomaly detection algorithms and frameworks leveraging foundation models.
• Application-specific anomaly detection using foundation models, including but not limited to finance, healthcare, cybersecurity, and industrial systems.
• Evaluation metrics and benchmarks for assessing anomaly detection in foundation models.
• Techniques for enhancing the explainability and interpretability of foundation models in anomaly detection tasks.
• Strategies for ensuring fairness and reducing bias in anomaly detection with foundation models.
• Privacy-preserving methods in anomaly detection using foundation models.
• Trustworthiness and reliability of foundation models in critical anomaly detection applications.
• Cross-disciplinary approaches for improving anomaly detection, incorporating insights from other fields such as psychology and sociology.
• Incremental learning and adaptation mechanisms for foundation models in dynamic environments.
• Integration of domain knowledge and expert systems with foundation models for improved anomaly detection.
• Exploring the limitations and challenges of current foundation models in detecting anomalies in complex and noisy data.
• Forward-looking perspectives on the evolution of anomaly detection methodologies with the advancement of foundation models.

 

Instructions of Publication Preparation

We plan to publish the accepted papers with the Springer CCIS series. For the authors of the accpeted papers, please format your paper using the official Springer template and follow the instructions on the Springer author guideline and author information. Please also submit all the source files (compressed as a .zip file) together with the compiled .pdf file and the signed License to Publish Agreement via CMT. If the camera ready paper, the corresponding LaTeX source file, and the license to publish agreement are not submitted in the correct format on time, then the publication of the paper cannot be guaranteed.

Camera ready deadline: June 14, 2024 AOE Time  

• GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection.
  Jiangning Zhang, Haoyang He, Xuhai Chen, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong Liu.


• CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection.
  Xuhai Chen, Jiangning Zhang, Guanzhong Tian, Haoyang He, Wuhao Zhang, Yabiao Wang, Chengjie Wang, Yong Liu.
  [video] [slides]


• Robust Self-Supervised Deep Tensor Decomposition for Corrupted Time Series Classification.
  Man Li, Ziyue Li, Lijun Sun, Fugee Tsung.


• DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning.
  Yangfan He, Xinyan Wang, Tianyu Shi.


• Dual Memory-guided Probabilistic Model for Weakly-supervised Anomaly Detection.
  Hsiu-Hua Chou, Ruyi Xu, Kang-Yang Huang, Jhih-Ciang Wu, Hong-Han Shuai, Wen-Huang Cheng.


• Zero-Shot Batch-Level Tabular Anomaly Detection Using LLMs.
  Aodong Li, Yunhan Zhao, Chen Qiu, Marius Kloft, Padhraic Smyth, Maja Rudolph, Stephan Mandt.
  [slides]

Chen Zhang	Tsinghua University
Dongliang Guo	University of Virginia
Hailing Wang	Tianjin University
Jianglin Lu	Northeastern University
Jiaqi Liu	Southern University of Science and Technology
Qifeng Wu	Northeastern University
Qihua Dong	Northeastern University
Yifan Wang	Northeastern University
Yitian Zhang	Northeastern University
Yunkang Cao	Huazhong University of Science and Technology
Zhi Xu	Northeastern University