Publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

  1. artlang_arch.png
    ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation
    Sylvia Yuan, Dan Wang, Ravi Ramamoorthi, and Xinrui Cui*
    arXiv, 2026
    A framework that enables open-vocabulary language control for reconstructed articulated objects by binding semantic language features to a 3D semantic-kinematic graph.
  2. teaser-artmesh.png
    ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
    Sylvia Yuan, Dan Wang, Ravi Ramamoorthi, and Xinrui Cui*
    arXiv, 2026
    A framework that improves articulated 3D object reconstruction by using a mesh-based rendering backbone instead of point-based Gaussian Splatting.
  3. teaser-physconvex.png
    PhysConvex: Physics-Informed 3D Dynamic Convex Radiance Fields for Reconstruction and Simulation
    Dan Wang, Xinrui Cui*, Serge Belongie, and Ravi Ramamoorthi
    In European Conference on Computer Vision, 2026 (27.5% acceptance rate)
    A 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.
  4. teaser-SR.png
    Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution
    Dan Wang, Haiyan Sun, Shan Du, Z. Jane Wang, Zhaochong An, Serge Belongie, and Xinrui Cui*
    arXiv, 2026
    A 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.
  5. teaser-YXLiu.png
    Interpretable Concept Evolution Flow in Diffusion Models
    Yuxuan Liu, Dan Wang, and Xinrui Cui*
    Coming soon, 2026
  6. flow-innerf.png
    InNeRF: Learning Interpretable Radiance Fields for Generalizable 3D Scene Representation and Rendering
    Dan Wang and Xinrui Cui*
    In ACM International Conference on Multimedia, Melbourne VIC, Australia, 2024 (26% acceptance rate)
    A unified, end-to-end Transformer-based framework for generalizable 3D scene representation and rendering that improves model interpretability and performance.
  7. flow-ZYZhang.png
    Distilling Invariant Representations with Domain Adversarial Learning for Cross-Subject Children Seizure Prediction
    Ziye Zhang, Aiping Liu, Yikai Gao, Xinrui Cui, Ruobing Qian, and Xun Chen
    IEEE Transactions on Cognitive and Developmental Systems, 2023 (impact factor: 4.7)
  8. flow-YKGao.png
    A general sample-weighted framework for epileptic seizure prediction
    Yikai Gao, Aiping Liu, Xinrui Cui, Ruobing Qian, and Xun Chen
    Computers in Biology and Medicine, 2022 (impact factor: 6.3)
  9. flow-evolt.png
    Multi-View 3D Reconstruction With Transformers
    Dan Wang, Xinrui Cui*, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, and Rabab Ward
    In International Conference on Computer Vision (ICCV Oral), Oct 2021 (acceptance rate: 3%)
    A novel Transformer-based framework for multi-view 3D reconstruction that effectively captures long-range dependencies across views, leading to improved reconstruction quality and robustness.
  10. flow-chain.jpg
    Interpreting Bottom-Up Decision-Making of CNNs via Hierarchical Inference
    Dan Wang, Xinrui Cui*, Xun Chen, Rabab Ward, and Z. Jane Wang
    IEEE Transactions on Image Processing, 2021 (impact factor: 15.3)
    An 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.
  11. fig2-chip.png
    CHIP: Channel-Wise Disentangled Interpretation of Deep Convolutional Neural Networks
    Xinrui Cui, Dan Wang, and Z. Jane Wang
    IEEE Transactions on Neural Networks and Learning Systems, 2020 (impact factor: 9.7)
    A 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.
  12. showcase-flowin.jpg
    Feature-Flow Interpretation of Deep Convolutional Neural Networks
    Xinrui Cui, Dan Wang, and Z. Jane Wang
    IEEE Transactions on Multimedia, 2020 (impact factor: 9.7)
    A 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.
  13. model0-mint.jpg
    Multi-Scale Interpretation Model for Convolutional Neural Networks: Building Trust Based on Hierarchical Interpretation
    Xinrui Cui, Dan Wang, and Z. Jane Wang
    IEEE Transactions on Multimedia, 2019 (impact factor: 9.7)
    A multi-scale interpretation model that provides hierarchical explanations of CNN predictions by interpreting the model’s decision-making process at multiple levels of abstraction.
  14. fig-SPaUnM.png
    Robust Sparse Unmixing for Hyperspectral Imagery
    Dan Wang, Zhenwei Shi, and Xinrui Cui
    IEEE Transactions on Geoscience and Remote Sensing, 2018 (impact factor: 9.4)
    A 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.
  15. flow-SLSeg.jpeg
    Multi-feature sea–land segmentation based on pixel-wise learning for optical remote-sensing imagery
    Dan Wang, Xinrui Cui, Fengying Xie, Zhiguo Jiang, and Zhenwei Shi
    International Journal of Remote Sensing, 2017 (impact factor: 2.6)
    A multi-feature sea–land segmentation method that leverages pixel-wise learning to improve the accuracy and robustness of optical remote-sensing imagery analysis.
  16. fig-globalsip.png
    Sparse unmixing based on feature pixels for hyperspectral imagery
    Xinrui Cui and Z. Jane Wang
    In 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017
  17. Modulation of electromagnetic wave absorption by carbon shell thickness in carbon encapsulated magnetite nanospindles–poly(vinylidene fluoride) composites
    Xiaofang Liu†, Xinrui Cui†, Yaxin Chen, Xiao-Juan Zhang, Ronghai Yu, Guang-Sheng Wang, and Hua Ma
    Carbon, 2015 (impact factor: 12.7)
  18. Flexible nanocomposites with enhanced microwave absorption properties based on Fe3O4/SiO2 nanorods and polyvinylidene fluoride
    Xiaofang Liu, Yaxin Chen, Xinrui Cui, Min Zeng, Ronghai Yu, and Guang-Sheng Wang
    Journal of Materials Chemistry A, 2015 (impact factor: 9.2)
  19. Stabilization of ultrafine metal nanocatalysts on thin carbon sheets
    Xiaofang Liu, Xinrui Cui, Yiding Liu, and Yadong Yin
    Nanoscale, 2015 (impact factor: 5.2)
  20. The structure and multifunctional behaviors of Mn–ZnO/Mn–ZnS nanocomposites
    Xiaofang Liu, Xiaobo Chen, Xinrui Cui, and Ronghai Yu
    Ceramics International, 2014 (impact factor: 6.0)
  21. Shell-enhanced photoluminescence and ferromagnetism of Co:ZnS/Co:ZnO core–shell nanostructure
    Xiaofang Liu, Xinrui Cui, Xiaobo Chen, Na Yang, and Ronghai Yu
    Materials Research Bulletin, 2014 (impact factor: 5.8)