31 citations · 67 across the 8 of their papers we have counts for
8 papers
1st Solution Places for CVPR 2023 UG+ Challenge Track 2.1-Text Recognition through Atmospheric Turbulence
Shengqi Xu, Xueyao Xiao, Shuning Cao +2
In this technical report, we present the solution developed by our team VIELab-HUST for text recognition through atmospheric turbulence in Track 2.1 of the CVPR 2023 UG+ chal…
Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
Yi Chang, Yun Guo, Yuntong Ye +5
Most of the existing learning-based deraining methods are supervisedly trained on synthetic rainy-clean pairs. The domain gap between the synthetic and real rain makes them less ge…
High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation
Shilv Cai, Zhijun Zhang, Liqun Chen +3
Learning-based methods have effectively promoted the community of image compression. Meanwhile, variational autoencoder (VAE) based variable-rate approaches have recently gained mu…
Category-Aware Transformer Network for Better Human-Object Interaction Detection
Leizhen Dong, Zhimin Li, Kunlun Xu +4
Human-Object Interactions (HOI) detection, which aims to localize a human and a relevant object while recognizing their interaction, is crucial for understanding a still image. Rec…
Unsupervised Image Deraining: Optimization Model Driven Deep CNN
Changfeng Yu, Yi Chang, Yi Li +2
The deep convolutional neural network has achieved significant progress for single image rain streak removal. However, most of the data-driven learning methods are full-supervised…
Effective Actor-centric Human-object Interaction Detection
Kunlun Xu, Zhimin Li, Zhijun Zhang +5
While Human-Object Interaction(HOI) Detection has achieved tremendous advances in recent, it still remains challenging due to complex interactions with multiple humans and objects…