Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
|
|
- Clinton Tucker
- 5 years ago
- Views:
Transcription
1 Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields Authors: Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh Presented by: Suraj Kesavan, Priscilla Jennifer ECS 289G: Visual Recognition 02/27/2018
2 Introduction to Pose Estimation and Association
3 Challenges Unknown number of people that can occur in a frame. Complex Spatial Interference - Contact, Occlusion between people. Variance in person scales Run time Complexity.
4 Top-down Approach: Person Detection + Pose Estimation Faster R-CNN (Person Detector) Papandreou, George, et al. "Towards accurate multiperson pose estimation in the wild." arxiv preprint arxiv: (2017). ResNet
5 Bottom-up Approach: Parts Detection and Parts Association Parts Detection Image CNN Parts Association
6 Sub-network 1: Part Detection S = (S1, S2, SJ), Si is a confidence map - for each part (j )
7 Sub-network 1: Part Detection p - (x, y) in an image W(p) - Binary mask {0, 1} Stj(p) - Confidence score for joint J {1.J} at stage t S*j(p) - Ground truth confidence map xj,k - Ground truth of body part j for person k S*j,k(p) - confidence score for joint j for person k Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No
8 Sub-network 1: Parts Detection
9 Sub-network 2: Part Association using Part Affinity Fields Part Affinity Fields encodes Orientation
10 Sub-network 2: Part Association using Part Affinity Fields L = (L1, L2, LC), Li is a vector field - for each limb (c ) v - normalized unit vector along Xj1,kXj2,k lc.k - distance between Xj1,kXj2,k σl - limb width nc(p) - No of non-zero vectors at point p for all k people Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No
11 CNN Architecture
12 Sequential Prediction with Learned Spatial Context Stage 1 P CNN Stage T Stage 2 P P CNN CNN pose%20estimation-cmu.pdf Right Wrist - Stage 1 Right Wrist - Stage 2 Right Wrist - Stage T
13 Jointly Learning Parts Detection and Parts Association Stage 1 Stage 2 P CNN 2nd Branch Part Affinity Fields Stage T P P CNN CNN Stage 2 Stage T P CNN CNN
14 OpenPose Pipeline
15 Testing - Non-maximum Suppression NMS 104fc8
16 Testing - Line Integral PAF l1 n1 n2 n3 n4 0/1 0/1 0/1 0/1 l2 0/1 0/1 0/1 0/1 l3 0/1 0/1 0/1 0/1 Bipartite graph Line integral n1 n2 n3 n4 l l l Weighted Bipartite graph
17 Midpoint Score Map for Part-to-Part Association
18 Spatial Ambiguity of the Midpoint Representation Correct Connection Wrong Connection
19 Increasing Midpoint Number Cannot Solve The Problem Correct Connection Wrong Connection
20 Part Affinity Fields Avoid Spatial Ambiguity Elbow Wrist Correct Connection Wrong Connection
21 Greedy algorithm for Graph matching Shoulder Elbow Wrist
22 Hungarian algorithm for Graph matching Shoulder E1 E2 S S E1 E2 W W Elbow Wrist
23 Hungarian algorithm for Graph matching Shoulder E1 E2 S S Elbow Maximum E = = E1 E2 W W Wrist
24 Hungarian algorithm for Graph matching Shoulder E1 E2 S S Elbow Maximum E = = E1 E2 W W Wrist
25
26 Results on the MPII Multi Person Dataset Comparison of map across other implementations on MPII Dataset. Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No Comparison of the graph matching algorithms on validation set.
27 Results on the MPII Multi Person Dataset map curves of different experiments Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No map curves at different stages of the experiment.
28 Results on COCO Challenge Validation Set Comparison of results from the top-down approach with this approach. Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No Comparison of techniques which use Convolutional Pose machines(cpm) with this approach.
29 Strength Robustness to early commitment Run time for this method only increases slowly with the no of people in the image. Runtime Analysis Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No
30 Weakness Failure cases Greedy algorithm can fail to give a perfect matching. It fails in certain cases of rare posture, false positives for statues, overlapping limbs. Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." CVPR. Vol. 1. No
31
32 Questions and Discussion.
ECE 6554:Advanced Computer Vision Pose Estimation
ECE 6554:Advanced Computer Vision Pose Estimation Sujay Yadawadkar, Virginia Tech, Agenda: Pose Estimation: Part Based Models for Pose Estimation Pose Estimation with Convolutional Neural Networks (Deep
More informationMSCOCO Keypoints Challenge Megvii (Face++)
MSCOCO Keypoints Challenge 2017 Megvii (Face++) Team members(keypoints & Detection): Yilun Chen* Zhicheng Wang* Xiangyu Peng Zhiqiang Zhang Gang Yu Chao Peng Tete Xiao Zeming Li Xiangyu Zhang Yuning Jiang
More informationarxiv: v1 [cs.cv] 24 Nov 2016
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields Zhe ao Tomas Simon Shih-En Wei Yaser Sheikh The Robotics Institute, arnegie Mellon University arxiv:6.85v [cs.v] 24 Nov 26 {zhecao,shihenw}@cmu.edu
More informationTowards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach Xingyi Zhou, Qixing Huang, Xiao Sun, Xiangyang Xue, Yichen Wei UT Austin & MSRA & Fudan Human Pose Estimation Pose representation
More informationDetecting and Parsing of Visual Objects: Humans and Animals. Alan Yuille (UCLA)
Detecting and Parsing of Visual Objects: Humans and Animals Alan Yuille (UCLA) Summary This talk describes recent work on detection and parsing visual objects. The methods represent objects in terms of
More informationHuman Pose Estimation using Global and Local Normalization. Ke Sun, Cuiling Lan, Junliang Xing, Wenjun Zeng, Dong Liu, Jingdong Wang
Human Pose Estimation using Global and Local Normalization Ke Sun, Cuiling Lan, Junliang Xing, Wenjun Zeng, Dong Liu, Jingdong Wang Overview of the supplementary material In this supplementary material,
More informationarxiv: v2 [cs.cv] 23 Jan 2019
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark Jiefeng Li 1, Can Wang 1, Hao Zhu 1, Yihuan Mao 2, Hao-Shu Fang 1, Cewu Lu 1 1 Shanghai Jiao Tong University, 2 Tsinghua University
More informationDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin
More informationRealtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields Zhe ao MU-RI-TR-17-18 April 217 Thesis ommittee: Yaser Sheikh Deva Ramanan Aayush Bansal Robotics Institute arnegie Mellon University
More informationEfficient Segmentation-Aided Text Detection For Intelligent Robots
Efficient Segmentation-Aided Text Detection For Intelligent Robots Junting Zhang, Yuewei Na, Siyang Li, C.-C. Jay Kuo University of Southern California Outline Problem Definition and Motivation Related
More informationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects
More informationSSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang
SSD: Single Shot MultiBox Detector Author: Wei Liu et al. Presenter: Siyu Jiang Outline 1. Motivations 2. Contributions 3. Methodology 4. Experiments 5. Conclusions 6. Extensions Motivation Motivation
More informationMask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma
Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left
More informationDeepPose & Convolutional Pose Machines
DeepPose & Convolutional Pose Machines Main Concepts 1. 2. 3. 4. CNN with regressor head. Object Localization. Bigger to smaller or Smaller to bigger view. Deep Supervised learning to prevent Vanishing
More informationEfficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields
Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields Yaadhav Raaj Haroon Idrees Gines Hidalgo Yaser Sheikh The Robotics Institute, Carnegie Mellon University {raaj@cmu.edu,
More informationYiqi Yan. May 10, 2017
Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field
More informationarxiv: v5 [cs.cv] 4 Feb 2018
RMPE: Regional Multi-Person Pose Estimation Hao-Shu Fang 1, Shuqin Xie 1, Yu-Wing Tai 2, Cewu Lu 1 1 Shanghai Jiao Tong University, China 2 Tencent YouTu fhaoshu@gmail.com qweasdshu@sjtu.edu.cn yuwingtai@tencent.com
More informationSpatial Localization and Detection. Lecture 8-1
Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday
More informationPose Proposal Networks
Pose Proposal Networks Taiki Sekii [0000 0002 1895 3075] Konica Minolta, Inc. taiki.sekii@konicaminolta.com Abstract. We propose a novel method to detect an unknown number of articulated 2D poses in real
More informationarxiv: v4 [cs.cv] 2 Sep 2017
RMPE: Regional Multi-Person Pose Estimation Hao-Shu Fang 1, Shuqin Xie 1, Yu-Wing Tai 2, Cewu Lu 1 1 Shanghai Jiao Tong University, China 2 Tencent YouTu fhaoshu@gmail.com qweasdshu@sjtu.edu.cn yuwingtai@tencent.com
More informationHuman Motion Reconstruction from Action Video Data Using a 3-Layer-LSTM
Human Motion Reconstruction from Action Video Data Using a 3-Layer-LSTM Jihee Hwang Stanford Computer Science jiheeh@stanford.edu Danish Shabbir Stanford Electrical Engineering danishs@stanford.edu Abstract
More informationObject Detection Based on Deep Learning
Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf
More informationFlow-Based Video Recognition
Flow-Based Video Recognition Jifeng Dai Visual Computing Group, Microsoft Research Asia Joint work with Xizhou Zhu*, Yuwen Xiong*, Yujie Wang*, Lu Yuan and Yichen Wei (* interns) Talk pipeline Introduction
More informationObject Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR
Object Detection CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR Problem Description Arguably the most important part of perception Long term goals for object recognition: Generalization
More informationMulti-Scale Structure-Aware Network for Human Pose Estimation
Multi-Scale Structure-Aware Network for Human Pose Estimation Lipeng Ke 1, Ming-Ching Chang 2, Honggang Qi 1, and Siwei Lyu 2 1 University of Chinese Academy of Sciences, Beijing, China 2 University at
More information3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing
3 Object Detection BVM 2018 Tutorial: Advanced Deep Learning Methods Paul F. Jaeger, of Medical Image Computing What is object detection? classification segmentation obj. detection (1 label per pixel)
More informationMulti-Scale Structure-Aware Network for Human Pose Estimation
Multi-Scale Structure-Aware Network for Human Pose Estimation Lipeng Ke 1, Ming-Ching Chang 2, Honggang Qi 1, Siwei Lyu 2 1 University of Chinese Academy of Sciences, Beijing, China 2 University at Albany,
More informationInternet of things that video
Video recognition from a sentence Cees Snoek Intelligent Sensory Information Systems Lab University of Amsterdam The Netherlands Internet of things that video 45 billion cameras by 2022 [LDV Capital] 2
More informationFinding Tiny Faces Supplementary Materials
Finding Tiny Faces Supplementary Materials Peiyun Hu, Deva Ramanan Robotics Institute Carnegie Mellon University {peiyunh,deva}@cs.cmu.edu 1. Error analysis Quantitative analysis We plot the distribution
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha
More informationPart Localization by Exploiting Deep Convolutional Networks
Part Localization by Exploiting Deep Convolutional Networks Marcel Simon, Erik Rodner, and Joachim Denzler Computer Vision Group, Friedrich Schiller University of Jena, Germany www.inf-cv.uni-jena.de Abstract.
More informationMask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi
Mask R-CNN By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Types of Computer Vision Tasks http://cs231n.stanford.edu/ Semantic vs Instance Segmentation Image
More informationClassifying a specific image region using convolutional nets with an ROI mask as input
Classifying a specific image region using convolutional nets with an ROI mask as input 1 Sagi Eppel Abstract Convolutional neural nets (CNN) are the leading computer vision method for classifying images.
More informationTeam G-RMI: Google Research & Machine Intelligence
Team G-RMI: Google Research & Machine Intelligence Alireza Fathi (alirezafathi@google.com) Nori Kanazawa, Kai Yang, George Papandreou, Tyler Zhu, Jonathan Huang, Vivek Rathod, Chen Sun, Kevin Murphy, et
More informationObject Detection on Self-Driving Cars in China. Lingyun Li
Object Detection on Self-Driving Cars in China Lingyun Li Introduction Motivation: Perception is the key of self-driving cars Data set: 10000 images with annotation 2000 images without annotation (not
More informationSupplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network
Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network Anurag Arnab and Philip H.S. Torr University of Oxford {anurag.arnab, philip.torr}@eng.ox.ac.uk 1. Introduction
More informationLecture 7: Semantic Segmentation
Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr
More informationR-FCN: Object Detection with Really - Friggin Convolutional Networks
R-FCN: Object Detection with Really - Friggin Convolutional Networks Jifeng Dai Microsoft Research Li Yi Tsinghua Univ. Kaiming He FAIR Jian Sun Microsoft Research NIPS, 2016 Or Region-based Fully Convolutional
More informationIntroduction to Deep Learning for Facial Understanding Part IV: Facial Understanding
Introduction to Deep Learning for Facial Understanding Part IV: Facial Understanding Raymond Ptucha, Rochester Institute of Technology, USA Tutorial-9 May 19, 018 www.nvidia.com/dli ptucha 1 R. Ptucha
More informationarxiv: v2 [cs.cv] 8 Apr 2018
Cascaded Pyramid Network for Multi-Person Pose Estimation Yilun Chen Zhicheng Wang Yuxiang Peng 1 Zhiqiang Zhang 2 Gang Yu Jian Sun 1 Tsinghua University 2 HuaZhong University of Science and Technology
More informationCombining PGMs and Discriminative Models for Upper Body Pose Detection
Combining PGMs and Discriminative Models for Upper Body Pose Detection Gedas Bertasius May 30, 2014 1 Introduction In this project, I utilized probabilistic graphical models together with discriminative
More informationMulti-scale Adaptive Structure Network for Human Pose Estimation from Color Images
Multi-scale Adaptive Structure Network for Human Pose Estimation from Color Images Wenlin Zhuang 1, Cong Peng 2, Siyu Xia 1, and Yangang, Wang 1 1 School of Automation, Southeast University, Nanjing, China
More informationEncoder-Decoder Networks for Semantic Segmentation. Sachin Mehta
Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:
More informationReal-Time Human Pose Recognition in Parts from Single Depth Images
Real-Time Human Pose Recognition in Parts from Single Depth Images Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake CVPR 2011 PRESENTER:
More informationarxiv: v2 [cs.cv] 14 Apr 2017
Towards Accurate Multi-person Pose Estimation in the Wild George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, Kevin Murphy Google, Inc. [gpapan, tylerzhu, kanazawa,
More informationStereo Human Keypoint Estimation
Stereo Human Keypoint Estimation Kyle Brown Stanford University Stanford Intelligent Systems Laboratory kjbrown7@stanford.edu Abstract The goal of this project is to accurately estimate human keypoint
More informationSupplementary Material Estimating Correspondences of Deformable Objects In-the-wild
Supplementary Material Estimating Correspondences of Deformable Objects In-the-wild Yuxiang Zhou Epameinondas Antonakos Joan Alabort-i-Medina Anastasios Roussos Stefanos Zafeiriou, Department of Computing,
More informationScene Text Recognition for Augmented Reality. Sagar G V Adviser: Prof. Bharadwaj Amrutur Indian Institute Of Science
Scene Text Recognition for Augmented Reality Sagar G V Adviser: Prof. Bharadwaj Amrutur Indian Institute Of Science Outline Research area and motivation Finding text in natural scenes Prior art Improving
More informationBenchmarking and Error Diagnosis in Multi-Instance Pose Estimation
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation Matteo Ruggero Ronchi Pietro Perona www.vision.caltech.edu/ mronchi perona@caltech.edu California Institute of Technology, Pasadena, CA,
More informationA Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation
A Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation Submission ID: 2065 Abstract Accurate keypoint localization of human pose needs diversified features:
More informationEstimating Human Pose in Images. Navraj Singh December 11, 2009
Estimating Human Pose in Images Navraj Singh December 11, 2009 Introduction This project attempts to improve the performance of an existing method of estimating the pose of humans in still images. Tasks
More informationHuman Pose Estimation with Deep Learning. Wei Yang
Human Pose Estimation with Deep Learning Wei Yang Applications Understand Activities Family Robots American Heist (2014) - The Bank Robbery Scene 2 What do we need to know to recognize a crime scene? 3
More informationSimple Baselines for Human Pose Estimation and Tracking
Simple Baselines for Human Pose Estimation and Tracking Bin Xiao 1, Haiping Wu 2, and Yichen Wei 1 1 Microsoft Research Asia, 2 University of Electronic Science and Technology of China {Bin.Xiao, v-haipwu,
More informationDeep Incremental Scene Understanding. Federico Tombari & Christian Rupprecht Technical University of Munich, Germany
Deep Incremental Scene Understanding Federico Tombari & Christian Rupprecht Technical University of Munich, Germany C. Couprie et al. "Toward Real-time Indoor Semantic Segmentation Using Depth Information"
More informationarxiv: v1 [cs.cv] 31 Mar 2016
Object Boundary Guided Semantic Segmentation Qin Huang, Chunyang Xia, Wenchao Zheng, Yuhang Song, Hao Xu and C.-C. Jay Kuo arxiv:1603.09742v1 [cs.cv] 31 Mar 2016 University of Southern California Abstract.
More informationVISION & LANGUAGE From Captions to Visual Concepts and Back
VISION & LANGUAGE From Captions to Visual Concepts and Back Brady Fowler & Kerry Jones Tuesday, February 28th 2017 CS 6501-004 VICENTE Agenda Problem Domain Object Detection Language Generation Sentence
More informationChannel Locality Block: A Variant of Squeeze-and-Excitation
Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan
More informationObject Detection by 3D Aspectlets and Occlusion Reasoning
Object Detection by 3D Aspectlets and Occlusion Reasoning Yu Xiang University of Michigan Silvio Savarese Stanford University In the 4th International IEEE Workshop on 3D Representation and Recognition
More informationProject 3 Q&A. Jonathan Krause
Project 3 Q&A Jonathan Krause 1 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations 2 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations
More informationSkin Lesion Attribute Detection for ISIC Using Mask-RCNN
Skin Lesion Attribute Detection for ISIC 2018 Using Mask-RCNN Asmaa Aljuhani and Abhishek Kumar Department of Computer Science, Ohio State University, Columbus, USA E-mail: Aljuhani.2@osu.edu; Kumar.717@osu.edu
More informationEasyChair Preprint. Synthetic image translation for football players pose estimation
EasyChair Preprint 785 Synthetic image translation for football players pose estimation Micha l Sypetkowski, Grzegorz Sarwas and Tomasz Trzciński EasyChair preprints are intended for rapid dissemination
More informationarxiv: v1 [cs.cv] 15 Oct 2018
Instance Segmentation and Object Detection with Bounding Shape Masks Ha Young Kim 1,2,*, Ba Rom Kang 2 1 Department of Financial Engineering, Ajou University Worldcupro 206, Yeongtong-gu, Suwon, 16499,
More informationObject Detection in Sports Videos
Object Detection in Sports Videos M. Burić, M. Pobar, M. Ivašić-Kos University of Rijeka/Department of Informatics, Rijeka, Croatia matija.buric@hep.hr, marinai@inf.uniri.hr, mpobar@inf.uniri.hr Abstract
More informationAssociative Embedding: End-to-End Learning for Joint Detection and Grouping
Associative Embedding: End-to-End Learning for Joint Detection and Grouping Alejandro Newell Computer Science and Engineering University of Michigan Ann Arbor, MI alnewell@umich.edu Zhiao Huang* Institute
More informationHybrid Cascade Model for Face Detection in the Wild Based on Normalized Pixel Difference and a Deep Convolutional Neural Network
Hybrid Cascade Model for Face Detection in the Wild Based on Normalized Pixel Difference and a Deep Convolutional Neural Network Darijan Marčetić [-2-6556-665X], Martin Soldić [-2-431-44] and Slobodan
More informationUsing k-poselets for detecting people and localizing their keypoints
Using k-poselets for detecting people and localizing their keypoints Georgia Gkioxari, Bharath Hariharan, Ross Girshick and itendra Malik University of California, Berkeley - Berkeley, CA 94720 {gkioxari,bharath2,rbg,malik}@berkeley.edu
More informationP-CNN: Pose-based CNN Features for Action Recognition. Iman Rezazadeh
P-CNN: Pose-based CNN Features for Action Recognition Iman Rezazadeh Introduction automatic understanding of dynamic scenes strong variations of people and scenes in motion and appearance Fine-grained
More informationLEARNING GRAPH DECOMPOSITION
LEARNING GRAPH DECOMPOSITION Anonymous authors Paper under double-blind review ABSTRACT We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut
More informationGeometry-aware Traffic Flow Analysis by Detection and Tracking
Geometry-aware Traffic Flow Analysis by Detection and Tracking 1,2 Honghui Shi, 1 Zhonghao Wang, 1,2 Yang Zhang, 1,3 Xinchao Wang, 1 Thomas Huang 1 IFP Group, Beckman Institute at UIUC, 2 IBM Research,
More informationDeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material
DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material Yi Li 1, Gu Wang 1, Xiangyang Ji 1, Yu Xiang 2, and Dieter Fox 2 1 Tsinghua University, BNRist 2 University of Washington
More informationDepth from Stereo. Dominic Cheng February 7, 2018
Depth from Stereo Dominic Cheng February 7, 2018 Agenda 1. Introduction to stereo 2. Efficient Deep Learning for Stereo Matching (W. Luo, A. Schwing, and R. Urtasun. In CVPR 2016.) 3. Cascade Residual
More informationSupporting Information
Supporting Information Ullman et al. 10.1073/pnas.1513198113 SI Methods Training Models on Full-Object Images. The human average MIRC recall was 0.81, and the sub-mirc recall was 0.10. The models average
More informationPhoto OCR ( )
Photo OCR (2017-2018) Xiang Bai Huazhong University of Science and Technology Outline VALSE2018, DaLian Xiang Bai 2 Deep Direct Regression for Multi-Oriented Scene Text Detection [He et al., ICCV, 2017.]
More informationMCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection
MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection ILSVRC 2016 Object Detection from Video Byungjae Lee¹, Songguo Jin¹, Enkhbayar Erdenee¹, Mi Young Nam², Young Gui Jung², Phill Kyu
More informationA novel template matching method for human detection
University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 A novel template matching method for human detection Duc Thanh Nguyen
More informationPose estimation using a variety of techniques
Pose estimation using a variety of techniques Keegan Go Stanford University keegango@stanford.edu Abstract Vision is an integral part robotic systems a component that is needed for robots to interact robustly
More informationAttentionNet for Accurate Localization and Detection of Objects. (To appear in ICCV 2015)
AttentionNet for Accurate Localization and Detection of Objects. (To appear in ICCV 2015) Donggeun Yoo, Sunggyun Park, Joon-Young Lee, Anthony Paek, In So Kweon. State-of-the-art frameworks for object
More informationFully Convolutional Networks for Semantic Segmentation
Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Chaim Ginzburg for Deep Learning seminar 1 Semantic Segmentation Define a pixel-wise labeling
More informationA Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) A Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation Wentao Liu, 1,2 Jie Chen,
More informationarxiv: v1 [cs.cv] 29 Sep 2016
arxiv:1609.09545v1 [cs.cv] 29 Sep 2016 Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge Adrian Bulat and Georgios Tzimiropoulos Computer Vision
More informationarxiv: v1 [cs.cv] 27 Mar 2016
arxiv:1603.08212v1 [cs.cv] 27 Mar 2016 Human Pose Estimation using Deep Consensus Voting Ita Lifshitz, Ethan Fetaya and Shimon Ullman Weizmann Institute of Science Abstract In this paper we consider the
More informationDeep Models for 3D Reconstruction
Deep Models for 3D Reconstruction Andreas Geiger Autonomous Vision Group, MPI for Intelligent Systems, Tübingen Computer Vision and Geometry Group, ETH Zürich October 12, 2017 Max Planck Institute for
More informationLecture 5: Object Detection
Object Detection CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 5: Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 Traditional Object Detection Algorithms Region-based
More informationRecognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)
Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding
More informationInstance-aware Semantic Segmentation via Multi-task Network Cascades
Instance-aware Semantic Segmentation via Multi-task Network Cascades Jifeng Dai, Kaiming He, Jian Sun Microsoft research 2016 Yotam Gil Amit Nativ Agenda Introduction Highlights Implementation Further
More informationarxiv: v1 [cs.cv] 16 Nov 2015
Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression Zhiao Huang hza@megvii.com Erjin Zhou zej@megvii.com Zhimin Cao czm@megvii.com arxiv:1511.04901v1 [cs.cv] 16 Nov 2015 Abstract Facial
More informationSupplementary Materials for Learning to Parse Wireframes in Images of Man-Made Environments
Supplementary Materials for Learning to Parse Wireframes in Images of Man-Made Environments Kun Huang, Yifan Wang, Zihan Zhou 2, Tianjiao Ding, Shenghua Gao, and Yi Ma 3 ShanghaiTech University {huangkun,
More informationCapsule Networks. Eric Mintun
Capsule Networks Eric Mintun Motivation An improvement* to regular Convolutional Neural Networks. Two goals: Replace max-pooling operation with something more intuitive. Keep more info about an activated
More informationSEMANTIC SEGMENTATION AVIRAM BAR HAIM & IRIS TAL
SEMANTIC SEGMENTATION AVIRAM BAR HAIM & IRIS TAL IMAGE DESCRIPTIONS IN THE WILD (IDW-CNN) LARGE KERNEL MATTERS (GCN) DEEP LEARNING SEMINAR, TAU NOVEMBER 2017 TOPICS IDW-CNN: Improving Semantic Segmentation
More informationGeneric Object Detection Using Improved Gentleboost Classifier
Available online at www.sciencedirect.com Physics Procedia 25 (2012 ) 1528 1535 2012 International Conference on Solid State Devices and Materials Science Generic Object Detection Using Improved Gentleboost
More informationarxiv: v3 [cs.cv] 18 Sep 2018
Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World Matteo Fabbri, Fabio Lanzi, Simone Calderara, Andrea Palazzi, Roberto Vezzani, and Rita Cucchiara arxiv:1803.08319v3 [cs.cv]
More informationCS381V Experiment Presentation. Chun-Chen Kuo
CS381V Experiment Presentation Chun-Chen Kuo The Paper Indoor Segmentation and Support Inference from RGBD Images. N. Silberman, D. Hoiem, P. Kohli, and R. Fergus. ECCV 2012. 50 100 150 200 250 300 350
More informationYOLO 9000 TAEWAN KIM
YOLO 9000 TAEWAN KIM DNN-based Object Detection R-CNN MultiBox SPP-Net DeepID-Net NoC Fast R-CNN DeepBox MR-CNN 2013.11 Faster R-CNN YOLO AttentionNet DenseBox SSD Inside-OutsideNet(ION) G-CNN NIPS 15
More informationCausal and compositional generative models in online perception
Causal and compositional generative models in online perception Michael Janner with Ilker Yildirim, Mario Belledonne, Chris8an Wallraven, Winrich Freiwald, Joshua Tenenbaum MIT July 28, 2017 London, UK
More informationarxiv: v1 [cs.cv] 21 Jan 2019
Skeleton-based Action Recognition of People Handling Objects Sunoh Kim 1 Kimin Yun 2 Jongyoul Park 2 Jin Young Choi 1 1 ASRI, Dept. of Electrical and Computer Eng., Seoul National University, South Korea
More informationDeep Learning for Vision
Deep Learning for Vision Presented by Kevin Matzen Quick Intro - DNN Feed-forward Sparse connectivity (layer to layer) Different layer types Recently popularized for vision [Krizhevsky, et. al. NIPS 2012]
More information3D Pose Estimation using Synthetic Data over Monocular Depth Images
3D Pose Estimation using Synthetic Data over Monocular Depth Images Wei Chen cwind@stanford.edu Xiaoshi Wang xiaoshiw@stanford.edu Abstract We proposed an approach for human pose estimation over monocular
More informationImproved Face Detection and Alignment using Cascade Deep Convolutional Network
Improved Face Detection and Alignment using Cascade Deep Convolutional Network Weilin Cong, Sanyuan Zhao, Hui Tian, and Jianbing Shen Beijing Key Laboratory of Intelligent Information Technology, School
More informationCascaded Pyramid Network for Multi-Person Pose Estimation
Cascaded Pyramid Network for Multi-Person Pose Estimation Gang YU yugang@megvii.com Megvii (Face++) Team members: Yilun Chen* Zhicheng Wang* Xiangyu Peng Zhiqiang Zhang Gang Yu Jian Sun (https://arxiv.org/abs/1711.07319)
More informationarxiv:submit/ [cs.cv] 13 Jan 2018
Benchmark Visual Question Answer Models by using Focus Map Wenda Qiu Yueyang Xianzang Zhekai Zhang Shanghai Jiaotong University arxiv:submit/2130661 [cs.cv] 13 Jan 2018 Abstract Inferring and Executing
More information