Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A convolutional Neural Aggregation Network Woojae Kim1, Jongyoo Kim2, Sewoong Ahn1,Jinwoo.

Slides:



Advertisements
Similar presentations
Adaptive Offset Subspace Self- Organizing Map with an Application to Handwritten Digit Recognition Huicheng Zheng, Pádraig Cunningham and Alexey Tsymbal.
Advertisements

Introduction to Image Quality Assessment
1 Blind Image Quality Assessment Based on Machine Learning 陈 欣
Spatial Pyramid Pooling in Deep Convolutional
Perceived video quality measurement Muhammad Saqib Ilyas CS 584 Spring 2005.
Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab
Video Tracking Using Learned Hierarchical Features
University of Toronto Aug. 11, 2004 Learning the “Epitome” of a Video Sequence Information Processing Workshop 2004 Vincent Cheung Probabilistic and Statistical.
MULTIMEDIA INPUT / OUTPUT TECHNOLOGIES
Department of computer science and engineering Evaluation of Two Principal Image Quality Assessment Models Martin Čadík, Pavel Slavík Czech Technical University.
Hierarchical Matching with Side Information for Image Classification
Skeleton Based Action Recognition with Convolutional Neural Network
Journal of Visual Communication and Image Representation
Marcus Barkowsky, Savvas Argyropoulos1 Towards a Hybrid Model Provide a structure with building blocks Provide a programming and evaluation environment.
Regionlets for Generic Object Detection IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 37, NO. 10, OCTOBER 2015 Xiaoyu Wang, Ming.
Local Stereo Matching Using Motion Cue and Modified Census in Video Disparity Estimation Zucheul Lee, Ramsin Khoshabeh, Jason Juang and Truong Q. Nguyen.
National Taiwan Normal A System to Detect Complex Motion of Nearby Vehicles on Freeways C. Y. Fang Department of Information.
Face Recognition based on 2D-PCA and CNN
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
Deep Learning for Dual-Energy X-Ray
Demo.
Faster R-CNN – Concepts
IEEE BIBM 2016 Xu Min, Wanwen Zeng, Ning Chen, Ting Chen*, Rui Jiang*
Data Mining, Neural Network and Genetic Programming
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
DNN-Based Urban Flow Prediction
Krishna Kumar Singh, Yong Jae Lee University of California, Davis
Saliency-guided Video Classification via Adaptively weighted learning
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
Combining CNN with RNN for scene labeling (segmentation)
Introductory Seminar on Research: Fall 2017
Mean Euclidean Distance Error (mm)
Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis
Human-level control through deep reinforcement learning
CNNs and compressive sensing Theoretical analysis
Introduction to Neural Networks
Tuning JPEG2000 Image Compression for Graphics Regions
Wei Liu, Chaofeng Chen and Kwan-Yee K. Wong
Convolutional Neural Networks for Visual Tracking
Figure 4. Testing minimal configurations with existing models for spatiotemporal recognition. (A-B) A binary classifier is trained to separate a positive.
Two-Stream Convolutional Networks for Action Recognition in Videos
Towards Understanding the Invertibility of Convolutional Neural Networks Anna C. Gilbert1, Yi Zhang1, Kibok Lee1, Yuting Zhang1, Honglak Lee1,2 1University.
Object Detection + Deep Learning
Introduction of MATRIX CAPSULES WITH EM ROUTING
Hairong Qi, Gonzalez Family Professor
8-3 RRAM Based Convolutional Neural Networks for High Accuracy Pattern Recognition and Online Learning Tasks Z. Dong, Z. Zhou, Z.F. Li, C. Liu, Y.N. Jiang,
Single Image Rolling Shutter Distortion Correction
MEgo2Vec: Embedding Matched Ego Networks for User Alignment Across Social Networks Jing Zhang+, Bo Chen+, Xianming Wang+, Fengmei Jin+, Hong Chen+, Cuiping.
Anomaly Detection in Crowded Scenes
Pattern recognition in gait activities using a floor sensor system
An Introduction to Computer Vision& Pattern Recognition Group
Outline Background Motivation Proposed Model Experimental Results
SPM2: Modelling and Inference
Visualizing and Understanding Convolutional Networks
Machine Learning based Data Analysis
Neural Network Pipeline CONTACT & ACKNOWLEDGEMENTS
Spatially Supervised Recurrent Neural Networks for Visual Object Tracking Authors: Guanghan Ning, Zhi Zhang, Chen Huang, Xiaobo Ren, Haohong Wang, Canhui.
Human-object interaction
Visual Manipulation Relationship Network for Autonomous Robotics
Natalie Lang Tomer Malach
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
Visual Grounding 专题报告 Lejian Ren 4.23.
Unrolling the shutter: CNN to correct motion distortions
End-to-End Facial Alignment and Recognition
Deep learning: Recurrent Neural Networks CV192
Week 3 Volodymyr Bobyr.
Week 7 Presentation Ngoc Ta Aidean Sharghi
SDSEN: Self-Refining Deep Symmetry Enhanced Network
What and How Well You Performed
Lark Kwon Choi, Alan Conrad Bovik
Presentation transcript:

Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A convolutional Neural Aggregation Network Woojae Kim1, Jongyoo Kim2, Sewoong Ahn1,Jinwoo Kim1, and Sanghoon Lee1 1Department of Electrical and Electronic Engineering, Yonsei University 2Microsoft Research, Beijing, China 2019/10/26 Yuwen Li

Motivations Temporal motion effect: i)temporal masking effect; ii)a severe error in the motion map makes spatial errors more visible to humans 2019/10/26 Yuwen Li

Motivations Temporal memory for quality judgment 2019/10/26 Yuwen Li

Contributions A Deep Video Quality Assessor (DeepVQA) to predict the spatio- temporal sensitivity map A Convolutional Neural Aggregation Network (CHAN) borrowing an idea from an 'attention mechanism' 2019/10/26 Yuwen Li

Related Works Spatio-temporal Visual Sensitivity: i)A spatio temporal contrast sensitivity function (CSF) ii)A natural video statistics (NVS) theory iii)Existing attempts using deep learning failed to consider motion properties. Temporal Pooling: i)Average pooling ii)Adaptively pool the temporal scores from the HVS perspective iii)'Neural Aggregation Network for Video Face Recognition' (CVPR2017) 2019/10/26 Yuwen Li

Framework 2019/10/26 Yuwen Li

Framework-Step 1 Input: Distorted frame: normalized after subtracting the lowpass filtered frames Spatial Error map: 2019/10/26 Yuwen Li

Framework-Step 1 Input: Frame Difference map: Temporal Error map: 2019/10/26 Yuwen Li

Framework-Step 1 Intermediate output: Spatio-temporal Sensitivity map: 2019/10/26 Yuwen Li

Framework-Step 1 Intermediate output: Perceptual Error map: 2019/10/26 Yuwen Li

Framework-Step 1 2019/10/26 Yuwen Li

Framework-Step 2 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Experiments 2019/10/26 Yuwen Li

Conclusion +How to tell a good story -Act like an integration of their previous work -Generalization ability -Hard to transform to NR-VQA 2019/10/26 Yuwen Li

References Yang, J., Ren, P., Zhang, D., Chen, D., Wen, F., Li, H., Hua, G., Yang, J., Li, H.,Dai, Y., et al.: Neural aggregation network for video face recognition. In: Proc.IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR). 2492–2495 Kim, J., Lee, S.: Deep learning of human visual sensitivity in image quality assessment framework. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR).(2017) 2019/10/26 Yuwen Li