Publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
-
arXiv, 2026A physics-informed framework that unifies visual rendering and physical simulation by representing deformable radiance fields as boundary-driven 3D dynamic convex primitives governed by reduced-order continuum mechanics, enabling the high-fidelity reconstruction of appearance, geometry, and physical properties. -
arXiv, 2026A spatial-semantic guided diffusion framework that integrates spatial-grounded textual guidance and semantic-enhanced visual guidance to achieve a superior balance in the perception-distortion trade-off, producing super-resolution results that are both perceptually realistic and structurally faithful. -
-
In ACM International Conference on Multimedia, Melbourne VIC, Australia, 2024A unified, end-to-end Transformer-based framework for generalizable 3D scene representation and rendering that improves model interpretability and performance. -
IEEE Transactions on Cognitive and Developmental Systems, 2023 -
Computers in Biology and Medicine, 2022 -
In International Conference on Computer Vision (ICCV Oral), Oct 2021A novel Transformer-based framework for multi-view 3D reconstruction that effectively captures long-range dependencies across views, leading to improved reconstruction quality and robustness. -
IEEE Transactions on Image Processing, 2021An interpretation scheme that explains CNN decision-making by backwardly decomposing high-level semantic concepts into a hierarchy of lower-level visual concepts across different network layers, mimicking the bottom-up hierarchical logic of human visual recognition. -
IEEE Transactions on Neural Networks and Learning Systems, 2020A channel-wise disentangled interpretation method that identifies the most influential channels in a CNN for a given prediction and disentangles their contributions to different visual concepts, providing a more detailed and interpretable explanation of the model’s decision-making process. -
IEEE Transactions on Multimedia, 2020A feature-flow interpretation method that learns the flow of information through a CNN by tracking the activation patterns of features across layers, revealing how different features contribute to the final prediction. -
IEEE Transactions on Multimedia, 2019A multi-scale interpretation model that provides hierarchical explanations of CNN predictions by interpreting the model’s decision-making process at multiple levels of abstraction. -
IEEE Transactions on Geoscience and Remote Sensing, 2018A robust sparse unmixing method for hyperspectral imagery that incorporates spatial information and a novel regularization term to improve the accuracy and robustness of unmixing results. -
International Journal of Remote Sensing, 2017A multi-feature sea–land segmentation method that leverages pixel-wise learning to improve the accuracy and robustness of optical remote-sensing imagery analysis. -
In 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017 - Journal of Materials Chemistry A, 2015
- Ceramics International, 2014
- Materials Research Bulletin, 2014