scholarly journals Rate-Distortion Optimized Frame Dropping for Multiuser Streaming and Conversational Videos

2008 ◽  
Vol 2008 ◽  
pp. 1-13 ◽  
Author(s):  
Wei Tu ◽  
Jacob Chakareski ◽  
Eckehard Steinbach
Keyword(s):  
Computational Complexity ◽  
Side Information ◽  
Rate Distortion ◽  
Experimental Results ◽  
Network Node ◽  
Frame Dropping ◽  
End To End ◽  
Streaming Videos ◽  
Transmission Overhead

We consider rate-distortion optimized strategies for dropping frames from multiple conversational and streaming videos sharing limited network node resources. The dropping strategies are based on side information that is extracted during encoding and is sent along the regular bitstream. The additional transmission overhead and the computational complexity of the proposed frame dropping schemes are analyzed. Our experimental results show that a significant improvement in end-to-end performance is achieved compared to priority-based random early dropping.

scholarly journals Block Compressed Sensing of Images Using Adaptive Granular Reconstruction

2016 ◽  
Vol 2016 ◽  
pp. 1-9
Author(s):  
Ran Li ◽  
Hongbing Liu ◽  
Yu Zeng ◽  
Yanling Li
Keyword(s):  
Computational Complexity ◽  
Compressed Sensing ◽  
Structural Characteristic ◽  
Rate Distortion ◽  
Reconstructed Image ◽  
Hard Thresholding ◽  
Low Computational Complexity ◽  
Principle Components Analysis ◽  
Reconstruction Performance ◽  
Block Compressed Sensing

In the framework of block Compressed Sensing (CS), the reconstruction algorithm based on the Smoothed Projected Landweber (SPL) iteration can achieve the better rate-distortion performance with a low computational complexity, especially for using the Principle Components Analysis (PCA) to perform the adaptive hard-thresholding shrinkage. However, during learning the PCA matrix, it affects the reconstruction performance of Landweber iteration to neglect the stationary local structural characteristic of image. To solve the above problem, this paper firstly uses the Granular Computing (GrC) to decompose an image into several granules depending on the structural features of patches. Then, we perform the PCA to learn the sparse representation basis corresponding to each granule. Finally, the hard-thresholding shrinkage is employed to remove the noises in patches. The patches in granule have the stationary local structural characteristic, so that our method can effectively improve the performance of hard-thresholding shrinkage. Experimental results indicate that the reconstructed image by the proposed algorithm has better objective quality when compared with several traditional ones. The edge and texture details in the reconstructed image are better preserved, which guarantees the better visual quality. Besides, our method has still a low computational complexity of reconstruction.

scholarly journals Texture Grouping and Statistical Optimization Based Mode Prediction Decision Algorithm for Fast HEVC Intra Coding

2021 ◽  
Author(s):  
Jianhua Wang ◽  
Feng Lin ◽  
Jing Zhao ◽  
Yongbing Long
Keyword(s):  
Computational Complexity ◽  
Video Coding ◽  
Rate Distortion ◽  
Statistical Optimization ◽  
Optimal Prediction ◽  
Statistical Probability ◽  
Decision Algorithm ◽  
Texture Information ◽  
Prediction Mode ◽  
Probability Optimization

Abstract HEVC (High Efficiency Video Coding), as one of the newest international video coding standard, can achieve about 50% bit rate reduction compared with H.264/AVC (Advanced Video Coding) at the same perceptual quality due to the use of flexible CTU(coding tree unit) structure, but at the same time, it also dramatically adds the higher computational complexity for HEVC. With the aim of reducing the computational complexity, a texture grouping and statistical optimization based mode prediction decision algorithm is proposed for HEVC intra coding in this paper. The contribution of this paper lies in the fact that we successfully use the texture information grouping and statistical probability optimization technology to rapidly determine the optimal prediction mode for the current PU, which can reduce many unnecessary prediction and calculation operations of HCost (Hadamard Cost) and RDCost (Rate Distortion Cost) in HEVC, thus saving much computation complexity for HEVC. Specially, in our scheme, firstly we group 35 intra prediction modes into 5 subsets of candidate modes list according to its texture information of edge in the current PU, and each subset only contains 11 intra prediction modes, which can greatly reduce many traversing number of candidate mode in RMD (Rough Mode Decision) from 35 to 11 prediction modes; Secondly we use the statistical probability of the first candidate modes in candidate modes list as well as MPM selected as the optimal prediction mode to reduce the number of candidate modes in RDO(Rate Distortion Optimization), which can reduce the number of candidate modes from 3+MPM or 8+MPM to 2 candidate modes; At last, we use the number of candidate modes determined above to quickly find the optimal prediction mode with the minimum RDCost by RDO process. As a result, the computational complexity of HEVC can be efficiently reduced by our proposed scheme. And the simulation results of our experiments show that our proposed intra mode prediction decision algorithm based on texture information grouping and statistical probability optimization in this paper can reduce about 46.13% computational complexity on average only at a cost of 0.67% bit rate increase and 0.056db PSNR decline compared with the standard reference HM16.1 algorithm.

scholarly journals Merge Operation Effect On Image Compression Using Fractal Technique

2007 ◽  
Vol 4 (1) ◽  
pp. 169-173
Author(s):  
Baghdad Science Journal
Keyword(s):  
Image Compression ◽  
Rate Distortion ◽  
Experimental Results ◽  
Fractal Image Compression ◽  
Fractal Image ◽  
Statistical Measures ◽  
Fast Decoding

Fractal image compression gives some desirable properties like fast decoding image, and very good rate-distortion curves, but suffers from a high encoding time. In fractal image compression a partitioning of the image into ranges is required. In this work, we introduced good partitioning process by means of merge approach, since some ranges are connected to the others. This paper presents a method to reduce the encoding time of this technique by reducing the number of range blocks based on the computing the statistical measures between them . Experimental results on standard images show that the proposed method yields minimize (decrease) the encoding time and remain the quality results passable visually.

scholarly journals Consistency-Check Edge Refinement for Deep Stereo Matching

2020 ◽  
Author(s):  
Fangrui Wu ◽  
Menglong Yang
Keyword(s):  
Computational Efficiency ◽  
Stereo Matching ◽  
Information Aggregation ◽  
Experimental Results ◽  
Global Information ◽  
Consistency Check ◽  
Filtering Method ◽  
Tightly Coupled ◽  
End To End ◽  
Public Datasets

Recent end-to-end CNN-based stereo matching algorithms obtain disparities through regression from a cost volume, which is formed by concatenating the features of stereo pairs. Some downsampling steps are often embedded in constructing cost volume for global information aggregation and computational efficiency. However, many edge details are hard to recover due to the imprudent upsampling process and ambiguous boundary predictions. To tackle this problem without training another edge prediction sub-network, we developed a novel tightly-coupled edge refinement pipeline composed of two modules. The first module implements a gentle upsampling process by a cascaded cost volume filtering method, aggregating global information without losing many details. On this basis, the second module concentrates on generating a disparity residual map for boundary pixels by sub-pixel disparity consistency check, to further recover the edge details. The experimental results on public datasets demonstrate the effectiveness of the proposed method.

scholarly journals Towards High-Level Intrinsic Exploration in Reinforcement Learning

2020 ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Reinforcement Learning ◽  
Time Horizon ◽  
State Of The Art ◽  
Experimental Results ◽  
Prior Work ◽  
Extrinsic Rewards ◽  
Intrinsic Reward ◽  
Long Time ◽  
End To End ◽  
High Level

Deep reinforcement learning (DRL) methods traditionally struggle with tasks where environment rewards are sparse or delayed, which entails that exploration remains one of the key challenges of DRL. Instead of solely relying on extrinsic rewards, many state-of-the-art methods use intrinsic curiosity as exploration signal. While they hold promise of better local exploration, discovering global exploration strategies is beyond the reach of current methods. We propose a novel end-to-end intrinsic reward formulation that introduces high-level exploration in reinforcement learning. Our curiosity signal is driven by a fast reward that deals with local exploration and a slow reward that incentivizes long-time horizon exploration strategies. We formulate curiosity as the error in an agent’s ability to reconstruct the observations given their contexts. Experimental results show that this high-level exploration enables our agents to outperform prior work in several Atari games.

scholarly journals A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification

2018 ◽  
Author(s):  
Shuming Ma ◽  
Xu Sun ◽  
Junyang Lin ◽  
Xuancheng Ren
Keyword(s):  
Hierarchical Structure ◽  
Online Reviews ◽  
Text Summarization ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Joint Learning ◽  
End To End ◽  
Abstractive Summarization ◽  
Main Ideas ◽  
Different Levels

Text summarization and sentiment classification both aim to capture the main ideas of the text but at different levels. Text summarization is to describe the text within a few sentences, while sentiment classification can be regarded as a special type of summarization which ``summarizes'' the text into a even more abstract fashion, i.e., a sentiment class. Based on this idea, we propose a hierarchical end-to-end model for joint learning of text summarization and sentiment classification, where the sentiment classification label is treated as the further ``summarization'' of the text summarization output. Hence, the sentiment classification layer is put upon the text summarization layer, and a hierarchical structure is derived. Experimental results on Amazon online reviews datasets show that our model achieves better performance than the strong baseline systems on both abstractive summarization and sentiment classification.

scholarly journals Breakdown Detection in Negotiation Dialogues (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13969-13970
Author(s):  
Atsuki Yamaguchi ◽  
Katsuhide Fujita
Keyword(s):  
Artificial Intelligence ◽  
Natural Language ◽  
Language Model ◽  
Experimental Results ◽  
Conflicts Of Interests ◽  
Early Stages ◽  
End To End ◽  
Gated Recurrent Unit

In human-human negotiation, reaching a rational agreement can be difficult, and unfortunately, the negotiations sometimes break down because of conflicts of interests. If artificial intelligence can play a role in assisting with human-human negotiation, it can assist in avoiding negotiation breakdown, leading to a rational agreement. Therefore, this study focuses on end-to-end tasks for predicting the outcome of a negotiation dialogue in natural language. Our task is modeled using a gated recurrent unit and a pre-trained language model: BERT as the baseline. Experimental results demonstrate that the proposed tasks are feasible on two negotiation dialogue datasets, and that signs of a breakdown can be detected in the early stages using the baselines even if the models are used in a partial dialogue history.

Sign in / Sign up

Export Citation Format

Share Document