Video Compression Artifacts Removal with Efficient Non-local Block

2021 ◽  
Author(s):  
Dewang Hou ◽  
Yang Zhao ◽  
Ronggang Wang
Keyword(s):  
Video Compression ◽  
Artifacts Removal ◽  
Non Local ◽  
Local Block ◽  
Compression Artifacts

scholarly journals Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition

2019 ◽  
Vol 33 ◽  
pp. 8989-8996 ◽  
Author(s):  
Yu-Hui Wen ◽  
Lin Gao ◽  
Hongbo Fu ◽  
Fang-Lue Zhang ◽  
Shihong Xia
Keyword(s):  
Spatial Structure ◽  
Action Recognition ◽  
Large Scale ◽  
Human Skeleton ◽  
Semantic Roles ◽  
Temporal Domain ◽  
Non Local ◽  
Novel Model ◽  
Local Block ◽  
Skeleton Structure

Hierarchical structure and different semantic roles of joints in human skeleton convey important information for action recognition. Conventional graph convolution methods for modeling skeleton structure consider only physically connected neighbors of each joint, and the joints of the same type, thus failing to capture highorder information. In this work, we propose a novel model with motif-based graph convolution to encode hierarchical spatial structure, and a variable temporal dense block to exploit local temporal information over different ranges of human skeleton sequences. Moreover, we employ a non-local block to capture global dependencies of temporal domain in an attention mechanism. Our model achieves improvements over the stateof-the-art methods on two large-scale datasets.

scholarly journals PEA265: Perceptual Assessment of Video Compression Artifacts

2020 ◽  
Vol 30 (11) ◽  
pp. 3898-3910 ◽  
Author(s):  
Liqun Lin ◽  
Shiqi Yu ◽  
Liping Zhou ◽  
Weiling Chen ◽  
Tiesong Zhao ◽  
...  
Keyword(s):  
Video Compression ◽  
Perceptual Assessment ◽  
Compression Artifacts

scholarly journals Impact of Video Compression and Multimodal Embedding on Scene Description

Electronics ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 963
Author(s):  
Jin Young Lee
Keyword(s):  
Deep Learning ◽  
Video Compression ◽  
Automatic Generation ◽  
Image Motion ◽  
Label Information ◽  
Scene Description ◽  
The Impact ◽  
Potential Issue ◽  
Simple Network ◽  
Compression Artifacts

Scene description refers to the automatic generation of natural language descriptions from videos. In general, deep learning-based scene description networks utilize multimodalities, such as image, motion, audio, and label information, to improve the description quality. In particular, image information plays an important role in scene description. However, scene description has a potential issue, because it may handle images with severe compression artifacts. Hence, this paper analyzes the impact of video compression on scene description, and then proposes a simple network that is robust to compression artifacts. In addition, a network cascading more encoding layers for efficient multimodal embedding is also proposed. Experimental results show that the proposed network is more efficient than conventional networks.

Sign in / Sign up

Export Citation Format

Share Document