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},}
2024
IEEE-SPL
Palette-based Color Harmonization via Color Naming
Danna Xue, Javier Vazquez-Corral, Luis Herranz, Yanning Zhang, and Michael S. Brown
@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},}
CVIU
Take a prior from other tasks for severe blur removal
Pei Wang, Yu Zhu, Danna Xue, Qingsen Yan, Jinqiu Sun, Sung-eui Yoon, and Yanning Zhang
@article{wang2023take,title={Take a prior from other tasks for severe blur removal},author={Wang, Pei and Zhu, Yu and Xue, Danna and Yan, Qingsen and Sun, Jinqiu and Yoon, Sung-eui and Zhang, Yanning},journal={Computer Vision and Image Understanding},pages={104027},year={2024},publisher={Elsevier},}
IEEE-IV’25
Synth-to-Real Unsupervised Domain Adaptation for Instance Segmentation
Yachan Guo, Yi Xiao, Danna Xue, Jose Luis Gomez Zurita, and Antonio M López
@article{yachan2024synth,title={Synth-to-Real Unsupervised Domain Adaptation for Instance Segmentation},author={Guo, Yachan and Xiao, Yi and Xue, Danna and Zurita, Jose Luis Gomez and L{\'o}pez, Antonio M},journal={arXiv preprint arXiv:2405.09682},year={2024},}
2023
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
@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
@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},}
PR
Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance
Rui Li, Danna Xue, Shaolin Su, Xiantuo He, Qing Mao, Yu Zhu, Jinqiu Sun, and Yanning Zhang
@article{li2023learning,title={Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance},author={Li, Rui and Xue, Danna and Su, Shaolin and He, Xiantuo and Mao, Qing and Zhu, Yu and Sun, Jinqiu and Zhang, Yanning},journal={Pattern Recognition},volume={137},pages={109297},year={2023},publisher={Elsevier},}
2022
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
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},}
IEEE-TMM
Self-supervised monocular depth estimation with frequency-based recurrent refinement
Rui Li, Danna Xue, Yu Zhu, Hao Wu, Jinqiu Sun, and Yanning Zhang
@article{li2022self,title={Self-supervised monocular depth estimation with frequency-based recurrent refinement},author={Li, Rui and Xue, Danna and Zhu, Yu and Wu, Hao and Sun, Jinqiu and Zhang, Yanning},journal={IEEE Transactions on Multimedia},volume={25},pages={5626--5637},year={2022},publisher={IEEE},}
