351 citations · 1.1k across the 28 of their papers we have counts for
29 papers
Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting
Kaidong Zhang, Jialun Peng, Jingjing Fu +1
Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for…
Spatial-then-Temporal Self-Supervised Learning for Video Correspondence
Rui Li, Dong Liu
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervise…
Flow-Guided Transformer for Video Inpainting
Kaidong Zhang, Jingjing Fu, Dong Liu
We propose a flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fideli…
Recurrent Dynamic Embedding for Video Object Segmentation
Mingxing Li, Li Hu, Zhiwei Xiong +3
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the…
Neural Compression-Based Feature Learning for Video Restoration
Cong Huang, Jiahao Li, Bin Li +2
How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated informatio…
Motion-Focused Contrastive Learning of Video Representations
Rui Li, Yiheng Zhang, Zhaofan Qiu +3
Motion, as the most distinct phenomenon in a video to involve the changes over time, has been unique and critical to the development of video representation learning. In this paper…
Attribute Artifacts Removal for Geometry-based Point Cloud Compression
Xihua Sheng, Li Li, Dong Liu +1
Geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, e…
Temporal Context Mining for Learned Video Compression
Xihua Sheng, Jiahao Li, Bin Li +3
We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only t…
iWave3D: End-to-end Brain Image Compression with Trainable 3-D Wavelet Transform
Dongmei Xue, Haichuan Ma, Li Li +2
With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compres…
End-to-End Image Compression with Probabilistic Decoding
Haichuan Ma, Dong Liu, Cunhui Dong +2
Lossy image compression is a many-to-one process, thus one bitstream corresponds to multiple possible original images, especially at low bit rates. However, this nature was seldom…
Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules
Haisheng Fu, Feng Liang, Jianping Lin +7
Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versat…
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
Jialun Peng, Dong Liu, Songcen Xu +1
Given an incomplete image without additional constraint, image inpainting natively allows for multiple solutions as long as they appear plausible. Recently, multiplesolution inpain…
Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting
Shunxin Xu, Ke Sun, Dong Liu +2
The capability of image semantic segmentation may be deteriorated due to noisy input image, where image denoising prior to segmentation helps. Both image denoising and semantic seg…
Learned Variable-Rate Multi-Frequency Image Compression using Modulated Generalized Octave Convolution
Jianping Lin, Mohammad Akbari, Haisheng Fu +7
In this proposal, we design a learned multi-frequency image compression approach that uses generalized octave convolutions to factorize the latent representations into high-frequen…
Learning Trailer Moments in Full-Length Movies
Lezi Wang, Dong Liu, Rohit Puri +1
A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient. But a lack of annotations makes the existing approaches not app…
Efficient Integer-Arithmetic-Only Convolutional Neural Networks
Hengrui Zhao, Dong Liu, Houqiang Li
Integer-arithmetic-only networks have been demonstrated effective to reduce computational cost and to ensure cross-platform consistency. However, previous works usually report a de…
Foreground-Background Imbalance Problem in Deep Object Detectors: A Review
Joya Chen, Qi Wu, Dong Liu +1
Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision. Nevertheless,…
Transferring and Regularizing Prediction for Semantic Segmentation
Yiheng Zhang, Zhaofan Qiu, Ting Yao +3
Semantic segmentation often requires a large set of images with pixel-level annotations. In the view of extremely expensive expert labeling, recent research has shown that the mode…
M-LVC: Multiple Frames Prediction for Learned Video Compression
Jianping Lin, Dong Liu, Houqiang Li +1
We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduce…
Is There Tradeoff between Spatial and Temporal in Video Super-Resolution?
Haochen Zhang, Dong Liu, Zhiwei Xiong
Recent advances of deep learning lead to great success of image and video super-resolution (SR) methods that are based on convolutional neural networks (CNN). For video SR, advance…
Dual Temporal Memory Network for Efficient Video Object Segmentation
Kaihua Zhang, Long Wang, Dong Liu +3
Video Object Segmentation (VOS) is typically formulated in a semi-supervised setting. Given the ground-truth segmentation mask on the first frame, the task of VOS is to track and s…
Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC
Weiyao Lin, Xiaoyi He, Xintong Han +5
This paper addresses neural network based post-processing for the state-of-the-art video coding standard, High Efficiency Video Coding (HEVC). We first propose a partition-aware Co…
A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
Jiaying Liu, Dong Liu, Wenhan Yang +3
We present a comprehensive study and evaluation of existing single image compression artifacts removal algorithms, using a new 4K resolution benchmark including diversified foregro…
Is Heuristic Sampling Necessary in Training Deep Object Detectors?
Joya Chen, Dong Liu, Tong Xu +3
To train accurate deep object detectors under the extreme foreground-background imbalance, heuristic sampling methods are always necessary, which either re-sample a subset of all t…