Zobrazeno 1 - 10
of 2 507
pro vyhledávání: '"ZHANG Liqing"'
Autor:
Duan, Yuxuan, Hong, Yan, Zhang, Bo, Lan, Jun, Zhu, Huijia, Wang, Weiqiang, Zhang, Jianfu, Niu, Li, Zhang, Liqing
The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when
Externí odkaz:
http://arxiv.org/abs/2411.04571
Publikováno v:
CVPR (2024) 13395-13404
Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional reasoning. To address these chal
Externí odkaz:
http://arxiv.org/abs/2407.03008
Autor:
Dip, Sajib Acharjee, Shuvo, Uddip Acharjee, Chau, Tran, Song, Haoqiu, Choi, Petra, Wang, Xuan, Zhang, Liqing
Pathogen identification is pivotal in diagnosing, treating, and preventing diseases, crucial for controlling infections and safeguarding public health. Traditional alignment-based methods, though widely used, are computationally intense and reliant o
Externí odkaz:
http://arxiv.org/abs/2406.13133
Autor:
Lu, Lingxiao, Wu, Shengyi, Sun, Haoxuan, Gou, Junhong, Si, Jianlou, Qian, Chen, Zhang, Jianfu, Zhang, Liqing
Virtual clothes try-on has emerged as a vital feature in online shopping, offering consumers a critical tool to visualize how clothing fits. In our research, we introduce an innovative approach for virtual clothes try-on, utilizing a self-supervised
Externí odkaz:
http://arxiv.org/abs/2406.10539
Autor:
Zhong, Linhao, Hong, Yan, Chen, Wentao, Zhou, Binglin, Zhang, Yiyi, Zhang, Jianfu, Zhang, Liqing
Text-to-image generation models have seen considerable advancement, catering to the increasing interest in personalized image creation. Current customization techniques often necessitate users to provide multiple images (typically 3-5) for each custo
Externí odkaz:
http://arxiv.org/abs/2405.16501
Image inpainting, the task of reconstructing missing segments in corrupted images using available data, faces challenges in ensuring consistency and fidelity, especially under information-scarce conditions. Traditional evaluation methods, heavily dep
Externí odkaz:
http://arxiv.org/abs/2405.16263
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods. This paradigm decouples the training process into separate representation learning and classifier re-training. Previ
Externí odkaz:
http://arxiv.org/abs/2403.00250
Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background. Different from previous auto-encoder based harmonization networks, we develop a progressive multi-stage harmonization network, which harmoni
Externí odkaz:
http://arxiv.org/abs/2312.10264
Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the background. Despite the competitive performance of existing painterly harmoni
Externí odkaz:
http://arxiv.org/abs/2312.10263
Image compositing plays a vital role in photo editing. After inserting a foreground object into another background image, the composite image may look unnatural and inharmonious. When the foreground is photorealistic and the background is an artistic
Externí odkaz:
http://arxiv.org/abs/2311.08646