209 citations · 299 across the 24 of their papers we have counts for
21 papers · 1 filter
Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
Yingying Deng, Xiangyu He, Fan Tang +1
Style transfer presents a significant challenge, primarily centered on identifying an appropriate style representation. Conventional methods employ style loss, derived from second-…
Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition
Yunbing Jia, Xiaoyu Kong, Fan Tang +3
In this paper, we reveal the two sides of data augmentation: enhancements in closed-set recognition correlate with a significant decrease in open-set recognition. Through empirical…
Break-for-Make: Modular Low-Rank Adaptations for Composable Content-Style Customization
Yu Xu, Fan Tang, Juan Cao +5
Personalized generation paradigms empower designers to customize visual intellectual properties with the help of textual descriptions by tuning or adapting pre-trained text-to-imag…
MotionCrafter: One-Shot Motion Customization of Diffusion Models
Yuxin Zhang, Fan Tang, Nisha Huang +4
The essence of a video lies in its dynamic motions, including character actions, object movements, and camera movements. While text-to-video generative diffusion models have recent…
CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion
Nisha Huang, Weiming Dong, Yuxin Zhang +6
Although remarkable progress has been made in image style transfer, style is just one of the components of artistic paintings. Directly transferring extracted style features to nat…
: Zero-shot Style Transfer via Attention Rearrangement
Yingying Deng, Xiangyu He, Fan Tang +1
Despite the remarkable progress in image style transfer, formulating style in the context of art is inherently subjective and challenging. In contrast to existing learning/tuning m…
A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning
Yuxin Zhang, Fan Tang, Weiming Dong +4
We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style…
Region-Aware Diffusion for Zero-shot Text-driven Image Editing
Nisha Huang, Fan Tang, Weiming Dong +2
Image manipulation under the guidance of textual descriptions has recently received a broad range of attention. In this study, we focus on the regional editing of images with the g…
Inversion-Based Style Transfer with Diffusion Models
Yuxin Zhang, Nisha Huang, Fan Tang +4
The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes includi…
DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization
Nisha Huang, Yuxin Zhang, Fan Tang +5
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a st…
Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion
Nisha Huang, Fan Tang, Weiming Dong +1
Digital art synthesis is receiving increasing attention in the multimedia community because of engaging the public with art effectively. Current digital art synthesis methods usual…
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
Yuxin Zhang, Fan Tang, Weiming Dong +4
In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a…
CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
Chengcheng Ma, Xingjia Pan, Qixiang Ye +3
Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and u…
DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis
Shulan Ruan, Yong Zhang, Kun Zhang +4
Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually…
StyTr: Image Style Transfer with Transformers
Yingying Deng, Fan Tang, Weiming Dong +4
The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convoluti…
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Xingjia Pan, Yingguo Gao, Zhiwen Lin +5
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works s…
Arbitrary Video Style Transfer via Multi-Channel Correlation
Yingying Deng, Fan Tang, Weiming Dong +3
Video style transfer is getting more attention in AI community for its numerous applications such as augmented reality and animation productions. Compared with traditional image st…
Distribution Aligned Multimodal and Multi-Domain Image Stylization
Minxuan Lin, Fan Tang, Weiming Dong +3
Multimodal and multi-domain stylization are two important problems in the field of image style transfer. Currently, there are few methods that can perform both multimodal and multi…
Arbitrary Style Transfer via Multi-Adaptation Network
Yingying Deng, Fan Tang, Weiming Dong +3
Arbitrary style transfer is a significant topic with research value and application prospect. A desired style transfer, given a content image and referenced style painting, would r…
Multi-Attribute Guided Painting Generation
Minxuan Lin, Yingying Deng, Fan Tang +2
Controllable painting generation plays a pivotal role in image stylization. Currently, the control way of style transfer is subject to exemplar-based reference or a random one-hot…
Image Retargetability
Fan Tang, Weiming Dong, Yiping Meng +4
Real-world applications could benefit from the ability to automatically retarget an image to different aspect ratios and resolutions, while preserving its visually and semantically…