Xiao Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiao Cao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jiakui Hu
Peking University, Beijing, China
2 shared publications - Jialun Liu
Jilin University
2 shared publications - Liying Yang
School of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China
2 shared publications - Xuelong Li
Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China
2 shared publications - Chenhao Guan
SCSE, Macau University of Science and Technology, Macau, China
1 shared publication - Chi Zhang
Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSpatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSmart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2964-2972
Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning
Representation learning for images has been advanced by recent progress in more complex neural models such as the Vision Transformers and new learning theories such as the structural causal models. However, these models mainly rely on the classification loss to implicitly regularize the class-level data distributions, and they may face difficulties when handling classes with diverse visual patterns. We argue that the incorporation of the structural information between data samples may improve this situation. To achieve this goal, this paper presents a framework termed Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning (CSRMS), which includes the Class-level Relation Modelling, Class-aware Graph Sampling, and Relational Graph-Guided Representation Learning modules to model a relational graph of the entire dataset and perform class-aware smoothing and regularization operations to alleviate the issue of intra-class visual diversity and inter-class similarity. Specifically, the Class-level Relation Modelling module uses a clustering algorithm to learn the data distributions in the feature space and identify three types of class-level sample relations for the training set; Class-aware Graph Sampling module extends typical training batch construction process with three strategies to sample dataset-level sub-graphs; and Relational Graph-Guided Representation Learning module employs a graph convolution network with knowledge-guided smoothing operations to ease the projection from different visual patterns to the same class. Experiments demonstrate the effectiveness of structured knowledge modelling for enhanced representation learning and show that CSRMS can be incorporated with any state-of-the-art visual representation learning models for performance gains. The source codes and demos have been released at https://github.com/czt117/CSRMS.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2964-2972
Open AccessClass-level Structural Relation Modeling and Smoothing for Visual Representation Learning
Representation learning for images has been advanced by recent progress in more complex neural models such as the Vision Transformers and new learning theories such as the structural causal models. However, these models mainly rely on the classification loss to implicitly regularize the class-level data distributions, and they may face difficulties when handling classes with diverse visual patterns. We argue that the incorporation of the structural information between data samples may improve this situation. To achieve this goal, this paper presents a framework termed Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning (CSRMS), which includes the Class-level Relation Modelling, Class-aware Graph Sampling, and Relational Graph-Guided Representation Learning modules to model a relational graph of the entire dataset and perform class-aware smoothing and regularization operations to alleviate the issue of intra-class visual diversity and inter-class similarity. Specifically, the Class-level Relation Modelling module uses a clustering algorithm to learn the data distributions in the feature space and identify three types of class-level sample relations for the training set; Class-aware Graph Sampling module extends typical training batch construction process with three strategies to sample dataset-level sub-graphs; and Relational Graph-Guided Representation Learning module employs a graph convolution network with knowledge-guided smoothing operations to ease the projection from different visual patterns to the same class. Experiments demonstrate the effectiveness of structured knowledge modelling for enhanced representation learning and show that CSRMS can be incorporated with any state-of-the-art visual representation learning models for performance gains. The source codes and demos have been released at https://github.com/czt117/CSRMS.