SJTU Media Lab
SJTU Media Lab
News
People
Publications
Teaching
Resources
Jobs
Light
Dark
Automatic
paper-conference
Two-stream deep encoder-decoder architecture for fully automatic video object segmentation
We propose a two-stream Deep Encoder-Decoder architecture to tackle the task of fully automatic video object segmentation. Both two …
Jingwei Xu
,
Li Song
,
Rong Xie
Cite
DOI
Weight-based bit allocation scheme for VR videos in HEVC
Since VR videos shown on the head-mounted display (HMD) is omnidirectional, the average distortion of VR videos in all directions shall …
Bijia Li
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
The SJTU UHD 360-Degree Immersive Video Sequence Dataset
This paper presents a set of 12 new 8K resolution ultra-high definition (UHD) 360-degree immersive video sequences. This video …
Xu Liu
,
Yongcheng Huang
,
Li Song
,
Rong Xie
,
Xiaokang Yang
Cite
DOI
View-Dependent Omnidirectional Video Encapsulation Using Multiple Tracks
In recent years, there has been a significant interest towards virtual reality applications, especially omnidirectional videos. Due to …
Ying Luo
,
Li Song
,
Rong Xie
,
Chuanfei Luo
Cite
DOI
Lagrangian method based Rate-Distortion Optimization revisited for dependent video coding
Video encoding is based on the DPCM framework where temporal prediction coding introduces Rate-Distortion (RD) dependence. The RD …
Xiangwen Wang
,
Li Song
,
Zhengyi Luo
,
Rong Xie
Cite
DOI
Deep hash learning for efficient image retrieval
Hashing method is a widely used method for content-based image retrieval. For more complicated semantic similarity of images, …
Xuchao Lu
,
Li Song
,
Rong Xie
,
Xiaokang Yang
,
Wenjun Zhang
Cite
DOI
A Lightweight Distributed Media Processing System for Uhd Service
With the rapid development of media services, it’s an urgent demand that videos uploaded to the Internet need to be processed …
Xusheng Zhang
,
Li Song
,
Rong Xie
,
Yanan Zhao
Cite
DOI
Machine learning based VP9-to-HEVC video transcoding
As more and more coding standards are developed for videos with higher resolution and higher frame rates, the conversion between them …
Xiangyu Li
,
Rong Xie
,
Li Song
,
Liang Zhang
Cite
DOI
Two-stream recurrent convolutional neural networks for video saliency estimation
Recently, research has emphasized the need for video saliency estimation since its application covers a large domain. Traditional …
Xiao Wei
,
Li Song
,
Rong Xie
,
Wenjun Zhang
Cite
DOI
BEST: Benchmark and Evaluation of Surveillance Task
Smart/Intelligent video surveillance technology plays the central role in the emerging smart city systems. Most intelligent visual …
Chongyang Zhang
,
Bingbing Ni
,
Li Song
,
Guangtao Zhai
,
Xiaokang Yang
,
Wenjun Zhang
Cite
DOI
«
»
Cite
×