Danna Xue

I am currently a postdoctoral researcher in the Color in Context research group of Computer Vision Center (CVC) and Universitat Autònoma de Barcelona, Barcelona, Spain. I received my Ph.D. degree in July 2024 from Universitat Autònoma de Barcelona (UAB) and Northwestern Polytechnical University (NPU), co-supervised by Prof. Yanning Zhang, Assoc. Prof. Javier Vazquez Corral and Dr. Luis Herranz.

My research focuses on image interpretation and editing, particularly image and video segmentation and color manipulation. My work aims to develop advanced techniques for analyzing and modifying visual content, contributing to applications in computer vision and digital media.

news

Apr 12, 2025	One paper got accepted in CVPR2025. Thanks to my collaborators Maria Pilligua and Javier Vazquez-Corral!
Jul 12, 2024	Passed my thesis Defense Dobby is a free Elf! (only for this weekend…)

selected publications

CVPR’25
HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks

Maria Pilligua, Danna Xue, and Javier Vazquez-Corral

In International Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Abs arXiv Bib HTML PDF Website

Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural representations (INRs) trained independently for each video, making the process time-consuming when applied to new videos. Noticing this limitation, we propose a meta-learning strategy to learn a generic video decomposition model to speed up the training on new videos. Our model is based on a hypernetwork architecture which, given a video-encoder embedding, generates the parameters for a compact INR-based neural video decomposition model. Our strategy mitigates the problem of single-video overfitting and, importantly, shortens the convergence of video decomposition on new, unseen videos.
@inproceedings{pilligua2025hypernvd, title = {HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks}, author = {Pilligua, Maria and Xue, Danna and Vazquez-Corral, Javier}, booktitle = {International Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, }

IEEE-SPL

Palette-based Color Harmonization via Color Naming

Danna Xue, Javier Vazquez-Corral, Luis Herranz, Yanning Zhang, and Michael S. Brown

IEEE Signal Processing Letters, 2024

Bib HTML PDF Code

@article{xue2024palette,
  title = {Palette-based Color Harmonization via Color Naming},
  author = {Xue, Danna and Vazquez-Corral, Javier and Herranz, Luis and Zhang, Yanning and Brown, Michael S.},
  journal = {IEEE Signal Processing Letters},
  year = {2024},
  publisher = {IEEE},
}

CGF

Integrating high-level features for consistent palette-based multi-image recoloring

Danna Xue, Javier Vazquez-Corral, Luis Herranz, Yanning Zhang, and Michael S. Brown

In Computer Graphics Forum, 2023

Bib HTML PDF Code

@inproceedings{xue2023integrating,
  title = {Integrating high-level features for consistent palette-based multi-image recoloring},
  author = {Xue, Danna and Vazquez-Corral, Javier and Herranz, Luis and Zhang, Yanning and Brown, Michael S.},
  booktitle = {Computer Graphics Forum},
  pages = {e14964},
  year = {2023},
  organization = {Wiley Online Library},
}

ICASSP’23

Burst perception-distortion tradeoff: analysis and evaluation

Danna Xue, Luis Herranz, Javier Corral, and Yanning Zhang

In IEEE International Conference on Acoustics, Speech and Signal Processing, 2023

Bib HTML PDF

@inproceedings{xue2023burst,
  title = {Burst perception-distortion tradeoff: analysis and evaluation},
  author = {Xue, Danna and Herranz, Luis and Corral, Vazquez-Corral, Javier and Zhang, Yanning},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  pages = {1--5},
  year = {2023},
  organization = {IEEE},
}

ACM MM’22
Slimseg: Slimmable semantic segmentation with boundary supervision

Danna Xue, Fei Yang, Pei Wang, Luis Herranz, Jinqiu Sun, Yu Zhu, and Yanning Zhang

In ACM International Conference on Multimedia, 2022

Abs arXiv Bib HTML PDF Video

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these models cannot flexibly adapt to varying accuracy and efficiency requirements. In this paper, we propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference depending on the desired accuracy-efficiency tradeoff. More specifically, we employ parametrized channel slimming by stepwise downward knowledge distillation during training. Motivated by the observation that the differences between segmentation results of each submodel are mainly near the semantic borders, we introduce an additional boundary guided semantic segmentation loss to further improve the performance of each submodel. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance than independent models. Extensive experiments on semantic segmentation benchmarks, Cityscapes and CamVid, demonstrate the generalization ability of our framework.
@inproceedings{xue2022slimseg, title = {Slimseg: Slimmable semantic segmentation with boundary supervision}, author = {Xue, Danna and Yang, Fei and Wang, Pei and Herranz, Luis and Sun, Jinqiu and Zhu, Yu and Zhang, Yanning}, booktitle = {ACM International Conference on Multimedia}, pages = {6539--6548}, year = {2022}, }