activity
20152022
most citedSingle Image Blind Deblurring Using Multi-Scale Latent Structure Prior

95 citations · 370 across the 22 of their papers we have counts for

collaborators

36 papers

cs.CV202162 cited

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation

Wenkang Shan, Haopeng Lu, Shanshe Wang +2

Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead…

cs.CV20213 cited

Post-Training Quantization for Vision Transformer

Zhenhua Liu, Yunhe Wang, Kai Han +2

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers…

cs.CV20211 cited

Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement

Zefan Li, Chenxi Liu, Alan Yuille +3

Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. Bu…

cs.CV202131 cited

Recent Standard Development Activities on Video Coding for Machines

Wen Gao, Shan Liu, Xiaozhong Xu +3

In recent years, video data has dominated internet traffic and becomes one of the major data formats. With the emerging 5G and internet of things (IoT) technologies, more and more…

cs.MM2020

Sub-sampled Cross-component Prediction for Emerging Video Coding Standards

Junru Li, Meng Wang, Li Zhang +5

Cross-component linear model (CCLM) prediction has been repeatedly proven to be effective in reducing the inter-channel redundancies in video compression. Essentially speaking, the…

cs.CV2020

Intrinsic Temporal Regularization for High-resolution Human Video Synthesis

Lingbo Yang, Zhanning Gao, Peiran Ren +2

Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for hu…