Skip to main content

Research Repository

Advanced Search

Dr Frederick Li's Outputs (8)

MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment (2024)
Presentation / Conference Contribution
Zhou, K., Wang, L., Zhang, X., Shum, H. P. H., Li, F. W. B., Li, J., & Liang, X. (2024, September). MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment. Presented at ECCV 2024: The 18th European Conference on Computer Vision, Milan, Italy

Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs. However, the mi... Read More about MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment.

From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos (2024)
Presentation / Conference Contribution
Qiao, T., Li, R., Li, F. W. B., & Shum, H. P. H. (2024, December). From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos. Presented at Proceedings of the 2024 International Conference on Pattern Recognition, Kolkata, India, 2024., Kolkata, India

Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant stride... Read More about From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos.

Multi-Feature Fusion Enhanced Monocular Depth Estimation With Boundary Awareness (2024)
Journal Article
Song, C., Chen, Q., Li, F. W. B., Jiang, Z., Zheng, D., Shen, Y., & Yang, B. (2024). Multi-Feature Fusion Enhanced Monocular Depth Estimation With Boundary Awareness. Visual Computer, 40, 4955–4967. https://doi.org/10.1007/s00371-024-03498-w

Self-supervised monocular depth estimation has opened up exciting possibilities for practical applications, including scene understanding, object detection, and autonomous driving, without the need for expensive depth annotations. However, traditiona... Read More about Multi-Feature Fusion Enhanced Monocular Depth Estimation With Boundary Awareness.

Color Theme Evaluation through User Preference Modeling (2024)
Journal Article
Yang, B., Wei, T., Li, F. W. B., Liang, X., Deng, Z., & Fang, Y. (2024). Color Theme Evaluation through User Preference Modeling. ACM Transactions on Applied Perception, 21(3), 1-35. https://doi.org/10.1145/3665329

Color composition (or color theme) is a key factor to determine how well a piece of art work or graphical design is perceived by humans. Despite a few color harmony models have been proposed, their results are often less satisfactory since they mostl... Read More about Color Theme Evaluation through User Preference Modeling.

Multi-Style Cartoonization: Leveraging Multiple Datasets With GANs (2024)
Journal Article
Cai, J., Li, F. W. B., Nan, F., & Yang, B. (2024). Multi-Style Cartoonization: Leveraging Multiple Datasets With GANs. Computer Animation and Virtual Worlds, 35(3), Article e2269. https://doi.org/10.1002/cav.2269

Scene cartoonization aims to convert photos into stylized cartoons. While GANs can generate high-quality images, previous methods focus on individual images or single styles, ignoring relationships between datasets. We propose a novel multi-style sce... Read More about Multi-Style Cartoonization: Leveraging Multiple Datasets With GANs.

Laplacian Projection Based Global Physical Prior Smoke Reconstruction (2024)
Journal Article
Xiao, S., Tong, C., Zhang, Q., Cen, Y., Li, F. W. B., & Liang, X. (2024). Laplacian Projection Based Global Physical Prior Smoke Reconstruction. IEEE Transactions on Visualization and Computer Graphics, https://doi.org/10.1109/tvcg.2024.3358636

We present a novel framework for reconstructing fluid dynamics in real-life scenarios. Our approach leverages sparse view images and incorporates physical priors across long series of frames, resulting in reconstructed fluids with enhanced physical c... Read More about Laplacian Projection Based Global Physical Prior Smoke Reconstruction.

HSE: Hybrid Species Embedding for Deep Metric Learning (2024)
Presentation / Conference Contribution
Yang, B., Sun, H., Li, F. W. B., Chen, Z., Cai, J., & Song, C. (2024). HSE: Hybrid Species Embedding for Deep Metric Learning. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV51070.2023.01014

Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes. However, limited training samples restrict the model's generalization to downstream tasks. While addin... Read More about HSE: Hybrid Species Embedding for Deep Metric Learning.