Selected Journal Articles
-
ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
J. Wang, G. Kang
International Journal of Computer Vision (IJCV)
[PDF]
[Code]
-
PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
Y. Wang, X. Wei, M. Lu, G. Kang
IEEE Transactions on Image Processing (TIP)
[PDF]
[Code]
-
Normalizing Batch Normalization for Long-Tailed Recognition
Y. Bao, G. Kang, L. Yang, X. Duan, B. Zhao, B. Zhang
IEEE Transactions on Image Processing (TIP)
[PDF]
[Code]
-
Ov-vis: Open-vocabulary video instance segmentation
H. Wang, C. Yan, K. Chen, X. Jiang, X. Tang, Y. Hu, G. Kang, W. Xie, E. Gavves
International Journal of Computer Vision(IJCV)
[PDF]
-
Taking a closer look at factor disentanglement: Dual-path variational autoencoder learning for domain generalization
Y. Luo, G. Kang, K. Liu, F. Zhuang, J. Li
IEEE Transactions on Multimedia (TMM)
[PDF]
-
DropQueries: A Simple Way to Discover Comprehensive Segment Representations
H. Ding, B. Wang, G. Kang, W. Li, C. He, Y. Zhao, Y. Wei
IEEE Transactions on Multimedia (TMM)
[PDF]
-
Contrastive adaptation network for single-and multi-source domain adaptation
G. Kang, L. Jiang, Y. Wei, Y. Yang, A. Hauptmann
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
[PDF]
-
Shakeout: A new approach to regularized deep neural network training
G. Kang, J. Li, D. Tao
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
[PDF]
[Code]
Selected Conference Proceedings
2025
-
FreeInv: Free Lunch for Improving DDIM Inversion
Y Bao, H Liu, X Gao, H Fu, G. Kang
Neural Information Processing Systems (NeurIPS), 2025
[PDF]
-
Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models
N. Hu, X. Duan, J. Zhang, G. Kang
ACM International Conference on Multimedia (ACMMM), 2025
[PDF]
[Code]
-
Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models
H. Liu, J. Wang, S. Ma, J. Hu, X. Wei, G. Kang
ACM International Conference on Multimedia (ACMMM), 2025
[PDF]
[Code]
-
Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation
K. Mi, G. Kang, G. Li, L. Zhao, T. Zhou, C. Gong
ACM International Conference on Multimedia (ACMMM), 2025
[PDF]
[Code]
-
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection
C. Yan, J. Wang, L. Zhang, R. Zhao, X. Wu, K. Xiong, Q. Liu, G. Kang, Y. Kang
Annual Meeting of the Association for Computational Linguistics (ACL main),2025
[PDF]
[Code]
2024
-
Visa: Reasoning video object segmentation via large language models
C. Yan, H. Wang, S. Yan, X. Jiang, Y. Hu, G. Kang, W. Xie, E. Gavves
European Conference on Computer Vision (ECCV), 2024
[PDF]
[Code]
-
Tuning-free inversion-enhanced control for consistent image editing
X. Duan, S. Cui, G. Kang, B. Zhang, Z. Fei, M. Fan, J. Huang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
[PDF]
-
Learn to rectify the bias of CLIP for unsupervised semantic segmentation
J. Wang, G. Kang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[PDF]
[Code]
2023
-
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
G. Zhang, L. Wang, G. Kang, L. Chen, Y. Wei
International Conference on Computer Vision (ICCV) 2023
[PDF]
[Code]
-
Attriclip: A non-incremental learner for incremental knowledge learning
R. Wang, X. Duan, G. Kang, J. Liu, S. Lin, S. Xu, J. Li, B. Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[PDF]
[Code]
-
Adversarially masking synthetic to mimic real: Adaptive noise injection for point cloud segmentation adaptation
G. Li, G. Kang, X. Wang, Y. Wei, Y. Yang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[PDF]
2022 and Before
-
Few-shot segmentation via cycle-consistent transformer
G. Zhang, G. Kang, Y. Yang, Y. Wei
Neural Information Processing Systems (NeurIPS), 2021
[PDF]
[Code]
-
Domain consensus clustering for universal domain adaptation
G. Li, G. Kang, Y. Zhu, Y. Wei, Y. Yang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[PDF]
[Code]
-
Content-consistent matching for domain adaptive semantic segmentation
G. Li*, G. Kang*, W. Liu, Y. Wei, Y. Yang
European Conference on Computer Vision (ECCV), 2020
[PDF]
[Code]
-
Random erasing data augmentation
Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020
[PDF]
[Code]
-
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
G. Kang, Y. Wei, Y. Yang, Y. Zhuang, A. Hauptmann
Neural Information Processing Systems (NeurIPS Oral), 2020
[PDF]
[Code]
-
Contrastive adaptation network for unsupervised domain adaptation
G. Kang, L. Jiang, Y. Yang, A. Hauptmann
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[PDF]
[Code]
-
Annotation efficient cross-modal retrieval with adversarial attentive alignment
P.-Y. Huang, G. Kang, W. Liu, X. Chang, A. Hauptmann
ACM International Conference on Multimedia (ACMMM), 2019
[PDF]
-
Attract or distract: Exploit the margin of open set
Q. Feng, G. Kang, H. Fan, Y. Yang
International Conference on Computer Vision (ICCV), 2019
[PDF]
[Code]
-
Soft filter pruning for accelerating deep convolutional neural networks
Y. He, G. Kang, X. Dong, Y. Fu, Y. Yang
International Joint Conferences on Artificial Intelligence (IJCAI) 2018
[PDF]
[Code]
-
Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization
G. Kang, L. Zheng, Y. Yan, Y. Yang
European Conference on Computer Vision (ECCV),2018
[PDF]
-
Shakeout: A New Regularized Deep Neural Network Training Scheme
G. Kang, J. Li, D. Tao
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI Oral), 2016
[PDF]