CASIA OpenIR

Browse/Search Results:  1-6 of 6 Help

Selected(0)Clear Items/Page:    Sort:
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models 期刊论文
ACM TRANSACTIONS ON GRAPHICS, 2023, 卷号: 42, 期号: 6, 页码: 14
Authors:  Zhang, Yuxin;  Dong, Weiming;  Tang, Fan;  Huang, Nisha;  Huang, Haibin;  Ma, Chongyang;  Lee, Tong-Yee;  Deussen, Oliver;  Xu, Changsheng
Favorite  |  View/Download:65/0  |  Submit date:2024/03/26
Image generation  Diffusion models  Attribute-aware editing  Model personalization  
SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 5779-5793
Authors:  Chen, Dong;  Pan, Xingjia;  Tang, Fan;  Dong, Weiming;  Xu, Changsheng
Favorite  |  View/Download:57/0  |  Submit date:2024/02/22
High-order self-correlation  class activation map  structure preservation  weakly supervised object localization  
Semantic-Context Graph Network for Point-Based 3D Object Detection 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 11, 页码: 6474-6486
Authors:  Dong, Shuwei;  Kong, Xiaoyu;  Pan, Xingjia;  Tang, Fan;  Li, Wei;  Chang, Yi;  Dong, Weiming
Favorite  |  View/Download:134/0  |  Submit date:2023/12/21
3D object detection  graph neural networks  information entanglement  
A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning 期刊论文
ACM TRANSACTIONS ON GRAPHICS, 2023, 卷号: 42, 期号: 5, 页码: 16
Authors:  Zhang, Yuxin;  Tang, Fan;  Dong, Weiming;  Huang, Haibin;  Ma, Chongyang;  Lee, Tong-Yee;  Xu, Changsheng
Favorite  |  View/Download:144/0  |  Submit date:2023/12/21
Arbitrary style transfer  contrastive learning  style encoding  
PLDGAN: portrait line drawing generation with prior knowledge and conditioning target 期刊论文
VISUAL COMPUTER, 2023, 页码: 12
Authors:  Li, Sifei;  Wu, Fuzhang;  Fan, Yuqing;  Song, Xue;  Dong, Weiming
Favorite  |  View/Download:55/0  |  Submit date:2023/11/17
Portrait line drawings  Artistic stylization  Conditional generative adversarial networks  
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
Authors:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  Favorite  |  View/Download:167/26  |  Submit date:2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection