78 citations · 197 across the 21 of their papers we have counts for
21 papers
Debiasing Text-to-Image Diffusion Models
Ruifei He, Chuhui Xue, Haoru Tan +4
Learning-based Text-to-Image (TTI) models like Stable Diffusion have revolutionized the way visual content is generated in various domains. However, recent research has shown that…
Dataset Condensation via Generative Model
David Junhao Zhang, Heng Wang, Chuhui Xue +4
Dataset condensation aims to condense a large dataset with a lot of training samples into a small set. Previous methods usually condense the dataset into the pixels format. However…
Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
David Junhao Zhang, Mutian Xu, Chuhui Xue +4
Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additiona…
Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
Runyu Ding, Jihan Yang, Chuhui Xue +3
Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because…
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Yujun Shi, Chuhui Xue, Jun Hao Liew +5
Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DragGAN is an interactive point-based image editing framew…
PV3D: A 3D Generative Model for Portrait Video Generation
Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew +4
Recent advances in generative adversarial networks (GANs) have demonstrated the capabilities of generating stunning photo-realistic portrait images. While some prior works have app…
PLA: Language-Driven Open-Vocabulary 3D Scene Understanding
Runyu Ding, Jihan Yang, Chuhui Xue +3
Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D open-vocabulary perception is l…
Is synthetic data from generative models ready for image recognition?
Ruifei He, Shuyang Sun, Xin Yu +5
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applic…
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
Yujun Shi, Jian Liang, Wenqing Zhang +2
Federated learning aims to train models collaboratively across different clients without the sharing of data for privacy considerations. However, one major challenge for this learn…
1st Place Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: End-to-End Recognition of Out of Vocabulary Words
Zhangzi Zhu, Chuhui Xue, Yu Hao +2
Scene text recognition has attracted increasing interest in recent years due to its wide range of applications in multilingual translation, autonomous driving, etc. In this report,…
Runner-Up Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: Cropped Word Recognition
Zhangzi Zhu, Yu Hao, Wenqing Zhang +2
This report presents our 2nd place solution to ECCV 2022 challenge on Out-of-Vocabulary Scene Text Understanding (OOV-ST) : Cropped Word Recognition. This challenge is held in the…
Contextual Text Block Detection towards Scene Text Understanding
Chuhui Xue, Jiaxing Huang, Shijian Lu +2
Most existing scene text detectors focus on detecting characters or words that only capture partial text messages due to missing contextual information. For a better understanding…
VMRF: View Matching Neural Radiance Fields
Jiahui Zhang, Fangneng Zhan, Rongliang Wu +5
Neural Radiance Fields (NeRF) have demonstrated very impressive performance in novel view synthesis via implicitly modelling 3D representations from multi-view 2D images. However,…
Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Jingqun Tang, Wenqing Zhang, Hongye Liu +4
Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep representations. H…
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting
Chuhui Xue, Wenqing Zhang, Yu Hao +3
Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitive…
SeqFormer: Sequential Transformer for Video Instance Segmentation
Junfeng Wu, Yi Jiang, Song Bai +2
In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nev…
Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Xiang Bai, Hanchen Wang, Liya Ma +43
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection…
I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
Chuhui Xue, Jiaxing Huang, Wenqing Zhang +3
Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representa…
Scene Text Detection with Scribble Lines
Wenqing Zhang, Yang Qiu, Minghui Liao +3
Scene text detection, which is one of the most popular topics in both academia and industry, can achieve remarkable performance with sufficient training data. However, the annotati…
FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition
Wenqing Zhang, Yang Qiu, Song Bai +3
While scene text recognition techniques have been widely used in commercial applications, data privacy has rarely been taken into account by this research community. Most existing…
FIS-GAN: GAN with Flow-based Importance Sampling
Shiyu Yi, Donglin Zhan, Wenqing Zhang +3
Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation…