205 citations · 1.4k across the 102 of their papers we have counts for
20 papers · 1 filter
Reflash Dropout in Image Super-Resolution
Xiangtao Kong, Xina Liu, Jinjin Gu +2
Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic re…
A Simple Long-Tailed Recognition Baseline via Vision-Language Model
Teli Ma, Shijie Geng, Mengmeng Wang +5
The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-b…
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Changyao Tian, Wenhai Wang, Xizhou Zhu +2
Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning…
Self-slimmed Vision Transformer
Zhuofan Zong, Kunchang Li, Guanglu Song +4
Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bri…
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
David Junhao Zhang, Kunchang Li, Yali Wang +5
Recently, MLP-Like networks have been revived for image recognition. However, whether it is possible to build a generic MLP-Like architecture on video domain has not been explored,…
INTERN: A New Learning Paradigm Towards General Vision
Jing Shao, Siyu Chen, Yangguang Li +24
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However,…
Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning
Yihao Liu, Hengyuan Zhao, Kelvin C. K. Chan +4
Video colorization is a challenging and highly ill-posed problem. Although recent years have witnessed remarkable progress in single image colorization, there is relatively less re…
A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Images
Zijie Chen, Cheng Li, Junjun He +5
Radiation therapy (RT) is widely employed in the clinic for the treatment of head and neck (HaN) cancers. An essential step of RT planning is the accurate segmentation of various o…
Group Shift Pointwise Convolution for Volumetric Medical Image Segmentation
Junjun He, Jin Ye, Cheng Li +5
Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spati…
A New Journey from SDRTV to HDRTV
Xiangyu Chen, Zhengwen Zhang, Jimmy S. Ren +3
Nowadays modern displays are capable to render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most available resources are still in standard dynam…
Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Junhao Zhang, Yali Wang, Zhipeng Zhou +3
Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human…
Discovering Distinctive "Semantics" in Super-Resolution Networks
Yihao Liu, Anran Liu, Jinjin Gu +4
Image super-resolution (SR) is a representative low-level vision problem. Although deep SR networks have achieved extraordinary success, we are still unaware of their working mecha…
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Haisheng Su, Peiqin Zhuang, Yukun Li +4
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-S…
Prior-Induced Information Alignment for Image Matting
Yuhao Liu, Jiake Xie, Yu Qiao +2
Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image. However, most existing deep learning-based methods still suffer from the c…
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
Jinjin Gu, Haoming Cai, Chao Dong +47
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (…
HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
Xiangyu Chen, Yihao Liu, Zhengwen Zhang +2
Most consumer-grade digital cameras can only capture a limited range of luminance in real-world scenes due to sensor constraints. Besides, noise and quantization errors are often i…
TSI: Temporal Saliency Integration for Video Action Recognition
Haisheng Su, Kunchang Li, Jinyuan Feng +4
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to…
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
Yi Liu, Limin Wang, Yali Wang +2
Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of ac…
Smart Scribbles for Image Mating
Xin Yang, Yu Qiao, Shaozhe Chen +5
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles. Drawing a fne trimap requires a large amount of user effort, while…
Multi-scale Information Assembly for Image Matting
Yu Qiao, Yuhao Liu, Qiang Zhu +4
Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foregrou…