@article{zhang2025mate,
  title={MatE: Material Extraction from Single-Image via Geometric Prior},
  author={Zhang, Zeyu and Zhai, Wei and Yang, Jian and Cao, Yang},
  journal={arXiv preprint arXiv:2512.18312},
  year={2025}
}

@article{yang2025wemmu,
  title={WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens},
  author={Yang, Jian and Yin, Dacheng and He, Xiaoxuan and Li, Yong and Rao, Fengyun and Lyu, Jing and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2512.02536},
  year={2025}
}

@article{chen2025event,
title={Event Signal Filtering via Probability Flux Estimation},
author={Chen, Jinze and Zhai, Wei and Cao, Yang and Li, Bin and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2504.07503},
year={2025}
}

@article{chen2026unbiased,
  title={Unbiased Gradient Estimation for Event Binning via Functional Backpropagation},
  author={Chen, Jinze and Zhai, Wei and Han, Han and Ma, Tiankai and Cao, Yang and Li, Bin and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2602.12590},
  year={2026}
}

@article{wu2025alitok,
  title={AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model},
  author={Wu, Pingyu and Zhu, Kai and Liu, Yu and Tang, Longxiang and Yang, Jian and Peng, Yansong and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2506.05289},
  year={2025}
}

@article{wang2025towards,
  title={Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay},
  author={Wang, Kunyu and Fu, Xueyang and Cao, Chengzhi and Ge, Chengjie and Zhai, Wei and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2506.02477},
  year={2025}
}

@article{liao2024ef,
title={EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting},
author={Liao, Bohao and Zhai, Wei and Wan, Zengyu and Zhang, Tianzhu and Cao, Yang and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2410.15392},
year={2024}
}

@article{fang2025panoramic,
  title={Panoramic Video Generation with Pretrained Diffusion Models},
  author={Fang, Zixun and Zhu, Kai and Liu, Zhiheng and Liu, Yu and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2506.23513},
  year={2025}
}

@article{wang2025paid,
  title={PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation},
  author={Wang, Kunyu and Fu, Xueyang and Bao, Yuanfei and Ge, Chengjie and Cao, Chengzhi and Zhai, Wei and Zha, Zheng-Jun},
  journal={arXiv preprint arXiv:2506.02453},
  year={2025}
}

@article{huang2024leverage,
title={Leverage Task Context for Object Affordance Ranking},
author={Huang, Haojie and Luo, Hongchen and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2411.16082},
year={2024}
}

@article{yang2025sigman,
  title={SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets},
  author={Yang, Yuhang and Liu, Fengqi and Lu, Yixing and Zhao, Qin and Wu, Pingyu and Zhai, Wei and Yi, Ran and Cao, Yang and Ma, Lizhuang and Zha, Zheng-Jun and others},
  journal={arXiv preprint arXiv:2504.06982},
  year={2025}
}

@inproceedings{yu2025hero,
title={HERO: Human Reaction Generation from Videos},
author={Yu, Chengjun and Zhai, Wei and Yang, Yuhang and Cao, Yang and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2503.08270},
year={2025}
}

@article{han2024event,
title={Event-Based Tracking Any Point with Motion-Augmented Temporal Consistency},
author={Han, Han and Zhai, Wei and Cao, Yang and Li, Bin and Zha, Zheng-jun},
journal={arXiv preprint arXiv:2412.01300},
year={2024}
}

@article{wan2025emotive,
  title={EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation},
  author={Wan, Zengyu and Zhai, Wei and Cao, Yang and Zha, Zhengjun},
  journal={arXiv preprint arXiv:2503.11371},
  year={2025}
}

@article{zhang2024pear,
    title={PEAR: Phrase-Based Hand-Object Interaction Anticipation},
    author={Zhang, Zichen and Luo, Hongchen and Zhai, Wei and Cao, Yang and Kang, Yu},
    journal={arXiv preprint arXiv:2407.21510},
    year={2024}
    }

@inproceedings{wu2025brat,
  title={BRAT: Bidirectional Relative Positional Attention Transformer for Event-based Eye tracking},
  author={Wu, Yuliang and Han, Han and Chen, Jinze and Zhai, Wei and Cao, Yang and Zha, Zheng-jun},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={5136--5144},
  year={2025}
}

@article{lu2024benchmarking,
    title={Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning},
    author={Lu, Fan and Wu, Wei and Zheng, Kecheng and Ma, Shuailei and Gong, Biao and Liu, Jiawei and Zhai, Wei and Cao, Yang and Shen, Yujun and Zha, Zheng-Jun},
    journal={arXiv preprint arXiv:2412.08614},
    year={2024}
    }

@article{shao2024great,
title={GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding},
author={Shao, Yawen and Zhai, Wei and Yang, Yuhang and Luo, Hongchen and Cao, Yang and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2411.19626},
year={2024}
}

@article{wu2024improved,
title={Improved Video VAE for Latent Video Diffusion Model},
author={Wu, Pingyu and Zhu, Kai and Liu, Yu and Zhao, Liming and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
journal={arXiv preprint arXiv:2411.06449},
year={2024}
}

@article{yang2024mmar,
    title={MMAR: Towards Lossless Multi-Modal Auto-Regressive Prababilistic Modeling},
    author={Yang, Jian and Yin, Dacheng and Zhou, Yizhou and Rao, Fengyun and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
    journal={arXiv preprint arXiv:2410.10798},
    year={2024}
    }

@article{deng2024vmad,
    title={VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection},
    author={Deng, Huilin and Luo, Hongchen and Zhai, Wei and Cao, Yang and Kang, Yu},
    journal={arXiv preprint arXiv:2409.20146},
    year={2024}
    }

@article{lu2023likelihood,
    title={Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection},
    author={Lu, Fan and Zhu, Kai and Zheng, Kecheng and Zhai, Wei and Cao, Yang},
    journal={arXiv preprint arXiv:2312.01732},
    year={2023}
    }

@article{yang2024egochoir,
    title={EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views},
    author={Yang, Yuhang and Zhai, Wei and Wang, Chengfeng and Yu, Chengjun and Cao, Yang and Zha, Zheng-Jun},
    journal={arXiv preprint arXiv:2405.13659},
    year={2024}
    }

@article{wan2024event,
    title={Event-based Optical Flow via Transforming into Motion-dependent View},
    author={Wan, Zengyu and Wang, Yang and Wei, Zhai and Tan, Ganchao and Cao, Yang and Zha, Zheng-Jun},
    journal={IEEE Transactions on Image Processing},
    year={2024},
    publisher={IEEE}
    }

@article{zhang2024bidirectional,
    title={Bidirectional Progressive Transformer for Interaction Intention Anticipation},
    author={Zhang, Zichen and Luo, Hongchen and Zhai, Wei and Cao, Yang and Kang, Yu},
    journal={arXiv preprint arXiv:2405.05552},
    year={2024}
    }

@article{wu2024event,
    title={Event-based asynchronous HDR imaging by temporal incident light modulation},
    author={Wu, Yuliang and Tan, Ganchao and Chen, Jinze and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
    journal={Optics Express},
    volume={32},
    number={11},
    pages={18527--18538},
    year={2024},
    publisher={Optica Publishing Group}
    }

@article{deng2024prioritized,
    title={Prioritized Local Matching Network for Cross-Category Few-Shot Anomaly Detection},
    author={Deng, Huilin and Luo, Hongchen and Zhai, Wei and Cao, Yang and Kang, Yu},
    journal={IEEE Transactions on Artificial Intelligence},
    year={2024},
    publisher={IEEE}
    }

@inproceedings{yang2024lemon,
    title={LEMON: Learning 3D Human-Object Interaction Relation from 2D Images},
    author={Yang, Yuhang and Zhai, Wei and Luo, Hongchen and Cao, Yang and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={16284--16295},
    year={2024}
    }

@inproceedings{wang2024mambapupil,
    title={Mambapupil: Bidirectional selective recurrent model for event-based eye tracking},
    author={Wang, Zhong and Wan, Zengyu and Han, Han and Liao, Bohao and Wu, Yuliang and Zhai, Wei and Cao, Yang and Zha, Zheng-jun},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={5762--5770},
    year={2024}
    }

@inproceedings{liang2024hypercorrelation,
    title={Hypercorrelation Evolution for Video Class-Incremental Learning},
    author={Liang, Sen and Zhu, Kai and Zhai, Wei and Liu, Zhiheng and Cao, Yang},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={38},
    number={4},
    pages={3315--3323},
    year={2024}
    }

@article{luo2024grounded,
    title={Grounded affordance from exocentric view},
    author={Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    journal={International Journal of Computer Vision},
    volume={132},
    number={6},
    pages={1945--1969},
    year={2024},
    publisher={Springer}
    }

@article{zhai2023exploring,
    title={On exploring multiplicity of primitives and attributes for texture recognition in the wild},
    author={Zhai, Wei and Cao, Yang and Zhang, Jing and Xie, Haiyong and Tao, Dacheng and Zha, Zheng-Jun},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2023},
    publisher={IEEE}
    }

@article{zhai2024background,
    title={Background activation suppression for weakly supervised object localization and semantic segmentation},
    author={Zhai, Wei and Wu, Pingyu and Zhu, Kai and Cao, Yang and Wu, Feng and Zha, Zheng-Jun},
    journal={International Journal of Computer Vision},
    volume={132},
    number={3},
    pages={750--775},
    year={2024},
    publisher={Springer}
    }

@article{luo2023learning,
    title={Learning visual affordance grounding from demonstration videos},
    author={Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    journal={IEEE Transactions on Neural Networks and Learning Systems},
    year={2023},
    publisher={IEEE}
    }

@inproceedings{wu2023spatial,
    title={Spatial-aware token for weakly supervised object localization},
    author={Wu, Pingyu and Zhai, Wei and Cao, Yang and Luo, Jiebo and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={1844--1854},
    year={2023}
    }

@inproceedings{yang2023grounding,
    title={Grounding 3d object affordance from 2d interactions in images},
    author={Yang, Yuhang and Zhai, Wei and Luo, Hongchen and Cao, Yang and Luo, Jiebo and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={10905--10915},
    year={2023}
    }

@article{wang2024robustness,
    title={Robustness benchmark for unsupervised anomaly detection models},
    author={Wang, Pei and Zhai, Wei and Cao, Yang},
    journal={JUSTC},
    volume={54},
    number={1},
    pages={0103--1},
    year={2024},
    publisher={JUSTC}
    }

@inproceedings{luo2023leverage,
    title={Leverage interactive affinity for affordance learning},
    author={Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={6809--6819},
    year={2023}
    }

@inproceedings{lu2023uncertainty,
    title={Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection},
    author={Lu, Fan and Zhu, Kai and Zhai, Wei and Zheng, Kecheng and Cao, Yang},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={3282--3291},
    year={2023}
    }

@inproceedings{dong2023exploring,
    title={Exploring Tuning Characteristics of Ventral Stream’s Neurons for Few-Shot Image Classification},
    author={Dong, Lintao and Zhai, Wei and Zha, Zheng-Jun},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={37},
    number={1},
    pages={534--542},
    year={2023}
    }

@article{zhai2022exploring,
    title={Exploring figure-ground assignment mechanism in perceptual organization},
    author={Zhai, Wei and Cao, Yang and Zhang, Jing and Zha, Zheng-Jun},
    journal={Advances in Neural Information Processing Systems},
    volume={35},
    pages={17030--17042},
    year={2022}
    }

@article{lu2022phrase,
    title={Phrase-based affordance detection via cyclic bilateral interaction},
    author={Lu, Liangsheng and Zhai, Wei and Luo, Hongchen and Kang, Yu and Cao, Yang},
    journal={IEEE Transactions on Artificial Intelligence},
    year={2022},
    publisher={IEEE}
    }

@article{zhai2022one,
    title={One-shot object affordance detection in the wild},
    author={Zhai, Wei and Luo, Hongchen and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    journal={International Journal of Computer Vision},
    volume={130},
    number={10},
    pages={2472--2500},
    year={2022},
    publisher={Springer}
    }

@article{zhai2022deep,
    title={Deep texton-coherence network for camouflaged object detection},
    author={Zhai, Wei and Cao, Yang and Xie, HaiYong and Zha, Zheng-Jun},
    journal={IEEE Transactions on Multimedia},
    year={2022},
    publisher={IEEE}
    }

@article{li2022location,
    title={Location-free camouflage generation network},
    author={Li, Yangyang and Zhai, Wei and Cao, Yang and Zha, Zheng-jun},
    journal={IEEE Transactions on Multimedia},
    year={2022},
    publisher={IEEE}
    }

@inproceedings{luo2022learning,
    title={Learning affordance grounding from exocentric images},
    author={Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={2252--2261},
    year={2022}
    }

@inproceedings{wu2022background,
    title={Background activation suppression for weakly supervised object localization},
    author={Wu, Pingyu and Zhai, Wei and Cao, Yang},
    booktitle={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    pages={14228--14237},
    year={2022},
    organization={IEEE}
    }

@inproceedings{zhu2022self,
    title={Self-sustaining representation expansion for non-exemplar class-incremental learning},
    author={Zhu, Kai and Zhai, Wei and Cao, Yang and Luo, Jiebo and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={9296--9305},
    year={2022}
    }

@article{wang2022robust,
    title={Robust object detection via adversarial novel style exploration},
    author={Wang, Wen and Zhang, Jing and Zhai, Wei and Cao, Yang and Tao, Dacheng},
    journal={IEEE Transactions on Image Processing},
    volume={31},
    pages={1949--1962},
    year={2022},
    publisher={IEEE}
    }

@article{luo2021one,
    title={One-shot affordance detection},
    author={Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng},
    journal={arXiv preprint arXiv:2106.14747},
    year={2021}
    }

@article{li2021tri,
    title={A tri-attention enhanced graph convolutional network for skeleton-based action recognition},
    author={Li, Xingming and Zhai, Wei and Cao, Yang},
    journal={IET Computer Vision},
    volume={15},
    number={2},
    pages={110--121},
    year={2021},
    publisher={Wiley Online Library}
    }

@inproceedings{zhu2021self,
    title={Self-promoted prototype refinement for few-shot class-incremental learning},
    author={Zhu, Kai and Cao, Yang and Zhai, Wei and Cheng, Jie and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
    pages={6801--6810},
    year={2021}
    }

@inproceedings{zhu2021self,
    title={Self-supervised tuning for few-shot segmentation},
    author={Zhu, Kai and Zhai, Wei and Cao, Yang},
    booktitle={Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence},
    pages={1019--1025},
    year={2021}
    }

@inproceedings{wang2020deep,
    title={Deep inhomogeneous regularization for transfer learning},
    author={Wang, Wen and Zhai, Wei and Cao, Yang},
    booktitle={2020 IEEE International Conference on Image Processing (ICIP)},
    pages={221--225},
    year={2020},
    organization={IEEE}
    }

@inproceedings{zhai2020deep,
    title={Deep structure-revealed network for texture recognition},
    author={Zhai, Wei and Cao, Yang and Zha, Zheng-Jun and Xie, HaiYong and Wu, Feng},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={11010--11019},
    year={2020}
    }

@article{zhu2020one,
    title={One-shot texture retrieval using global grouping metric},
    author={Zhu, Kai and Cao, Yang and Zhai, Wei and Zha, Zheng-Jun},
    journal={IEEE Transactions on Multimedia},
    volume={23},
    pages={3726--3737},
    year={2020},
    publisher={IEEE}
    }

@inproceedings{zhai2019deep,
    title={Deep multiple-attribute-perceived network for real-world texture recognition},
    author={Zhai, Wei and Cao, Yang and Zhang, Jing and Zha, Zheng-Jun},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={3613--3622},
    year={2019}
    }

@article{zhu2019one,
    title={One-shot texture retrieval with global context metric},
    author={Zhu, Kai and Zhai, Wei and Zha, Zheng-Jun and Cao, Yang},
    journal={arXiv preprint arXiv:1905.06656},
    year={2019}
    }

@article{wu2019pixtextgan,
    title={PixTextGAN: structure aware text image synthesis for license plate recognition},
    author={Wu, Shilian and Zhai, Wei and Cao, Yang},
    journal={IET Image Processing},
    volume={13},
    number={14},
    pages={2744--2752},
    year={2019},
    publisher={Wiley Online Library}
    }

@inproceedings{zhai2018generative,
    title={A generative adversarial network based framework for unsupervised visual surface inspection},
    author={Zhai, Wei and Zhu, Jiang and Cao, Yang and Wang, Zengfu},
    booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    pages={1283--1287},
    year={2018},
    organization={IEEE}
    }

@inproceedings{zhu2018co,
    title={Co-occurrent structural edge detection for color-guided depth map super-resolution},
    author={Zhu, Jiang and Zhai, Wei and Cao, Yang and Zha, Zheng-Jun},
    booktitle={MultiMedia Modeling: 24th International Conference, MMM 2018, Bangkok, Thailand, February 5-7, 2018, Proceedings, Part I 24},
    pages={93--105},
    year={2018},
    organization={Springer}
    }