Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
|
|
- Robyn Hodges
- 5 years ago
- Views:
Transcription
1 The Visual Object Tracking Challenge Workshop 2016 Modeling and Propagating CNNs in a Tree Structure for Visual Tracking Hyeonseob Nam* Mooyeol Baek* Bohyung Han Dept. of Computer Science and Engineering *Equal contributors
2 Key concept 2 Multiple CNNs trained on tracking results from different time slices Modeling and propagating CNNs in a tree structure
3 Deep Learning for Visual Tracking Response map from CNN features HCF [Ma2016] FCNT [Wang2015] DeepSRDCF [Danelljan2015] 3 Pre-train CNN with tracking datasets MDNet [Nam2015]
4 Challenges Less training data Catastrophic forgetting 4 Online update Only a single labeled frame CNN forgets previous information Overfitting Difficult to train Unstable model Easily drifts
5 Our method CNNs trained on frames from different time slices State estimation Model update 5
6 Overall Algorithm 1 Initialize model with ground-truth 6 CNN1 1 st frame Model ground-truth positive patches negative patches
7 Overall Algorithm 2 Estimate target location for T consecutive frames 7 CNN1 (T+1) 23 nd rd st frame Model tracking results target candidates
8 Overall Algorithm 3 Update model 8 CNN1 21 nd st frame 31 rd st frame (T+1) 1 st st frame CNN2 Model tracking results positive patches negative patches Choose CNN with the best target score as a parent Maintain N latest CNNs
9 Overall Algorithm 4 Iterate until the end of sequence 9 CNN1 CNN2 (2T+1) (T+2) (T+3) nd rdst frame Model tracking results target candidates
10 Overall Algorithm 4 Iterate until the end of sequence 10 CNN1 (T+2) 1 st nd frame (T+3) 1 st rd frame (2T+1) 1 st frame st frame CNN2 Model CNN3 tracking results positive patches negative patches Choose CNN with the best target score as a parent Maintain N latest CNNs
11 Structure of CNN 11 Convolution layers are from VGG-M [Chatfield2014] network. Output: normalized vector [φ(x), 1 φ(x)] T Fully-connected layers are randomly initialized. Update fully-connected layers only (fc4, fc5, output)
12 State Estimation Weighted-average scores from multiple CNNs w N : min(max(φ N (x)), β N ) affinity of CNN N with t th frame reliability of CNN N 12 CNN w 1 CNN w 2 t th frame patch x* CNN 3 CNN N models w 3 w N scores φ N (x*) weights 0.79 score
13 Model Update 1 Sample training data for model update Store target scores of each CNN for parent selection 13 CNN w 1 CNN w 2 CNN w score t th frame patch CNN N models 0.66 w N scores weights positive patches negative patches score log
14 Model Update 2 14 Model CNN 1 Score log Target scores t+1 t+2 t+t Avg Disable old model (maintain N latest models) CNN 1 β 1 CNN 2 CNN max 0.91 CNN 2 β 2 CNN 3 β 3 CNN N 0.66 positive patches negative patches 0.91 CNN N+1 CNN N Finetune β N min. edge score along the path β N+1 =min(β 3,0.91)
15 Model Update an Example Soccer sequence 15 node: CNN image: representative training sample Multiple CNN captures multi-modal appearances Tree structure isolates erroneous models in a branch
16 Experiment Dataset VOT2016, VOT2015 [Kristan2015], OTB50 [Wu2013] 16 Experiment settings Parameters fixed throughout the whole experiment Speed: 1.5 fps Intel Core i7 3.3Ghz with NVIDIA TITAN X MATLAB / MatConvNet
17 Results VOT2016 Overlap: 0.56, Failures: 0.83, Unsupervised overlap: 0.49 Red box: tracking result, Black box: ground-truth <fish4> Overlap=0.45, Failures=0.00 <iceskater2> Overlap=0.62, Failures= <motocross1> Overlap=0.51, Failures=0.00 <nature> Overlap=0.58, Failures=2.00
18 Results VOT2015 [Kristan2015] 18 Trackers *MDNet excluded Accuracy Robustness Expected overlap ratio Rank Score Rank Score DSST [Danelljan2014] MUSTer [Hong2015CVPR] MEEM [Zhang2014] Struck [Hare2011] RAJSSC [Zhang2015] NSAMF [Li2014] SC-EBT [Wang2014] spst [Hua2015] LDP [Lukežič2016] SRDCF [Danelljan2015ICCV] EBT [Zhu2016] DeepSRDCF [Danelljan2015ICCVW] TCNN (ours) Red: best, Yellow: second best
19 Results OTB50 [Wu2013] 19 TCNN (ours) compared to state-of-the-art trackers HCF [Ma2016], CNN-SVM [Hong2015ICML], MEEM [Zhang2014], SRDCF [Danelljan2015ICCV], DeepSRDCF [Danelljan2015ICCVW], MUSTer [Hong2015CVPR], FCNT [Wang2015], DSST [Danelljan2014], Struck [Hare2011]
20 Ablation study Single Single CNN Linear Models propagating in a linear chain Tree-mean Models propagating in a tree structure Equal weights for every model Tree-weighted Models and weights propagating in a tree structure Results on OTB50 Variations Precision Success AUC Single Linear Tree-mean Tree-weighted
21 Comparison with MDNet Results on VOT2016 Results on OTB50 21 Trackers Accuracy Robustness MDNet-N Trackers Precision Success AUC MDNet-N TCNN (ours) TCNN (ours) MDNet MDNet MDNet-N: MDNet without pretraining using tracking videos
22 Conclusion Multiple CNNs are helpful to achieve multi-modality and reliability of target appearances. 22 The CNNs and their weights propagating in a tree structure efficiently isolates error in a temporal manner. Please refer to our arxiv paper for further details.
23 23 Thank you.
Towards Robust Visual Object Tracking: Proposal Selection & Occlusion Reasoning Yang HUA
Towards Robust Visual Object Tracking: Proposal Selection & Occlusion Reasoning Yang HUA PhD Defense, June 10 2016 Rapporteur Rapporteur Examinateur Examinateur Directeur de these Co-encadrant de these
More informationSupplementary Material
Supplementary Material ECO: Efficient Convolution Operators for Tracking Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg Computer Vision Laboratory, Department of Electrical Engineering,
More informationBeyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking Martin Danelljan, Andreas Robinson, Fahad Shahbaz Khan, Michael Felsberg 2 Discriminative Correlation Filters (DCF)
More informationOnline Object Tracking with Proposal Selection. Yang Hua Karteek Alahari Cordelia Schmid Inria Grenoble Rhône-Alpes, France
Online Object Tracking with Proposal Selection Yang Hua Karteek Alahari Cordelia Schmid Inria Grenoble Rhône-Alpes, France Outline 2 Background Our approach Experimental results Summary Background 3 Tracking-by-detection
More informationCREST: Convolutional Residual Learning for Visual Tracking
CREST: Convolutional Residual Learning for Visual Tracking Yibing Song, Chao Ma 2, Lijun Gong 3, Jiawei Zhang, Rynson W.H. Lau, and Ming-Hsuan Yang 4 City University of Hong Kong, Hong Kong 2 The University
More informationarxiv: v1 [cs.cv] 27 Oct 2015
Learning Multi-Domain Convolutional Neural Networks for Visual Tracking Hyeonseob Nam Bohyung Han Dept. of Computer Science and Engineering, POSTECH, Korea {namhs9, bhhan}@postech.ac.kr arxiv:.9v [cs.cv]
More informationFast CNN-Based Object Tracking Using Localization Layers and Deep Features Interpolation
Fast CNN-Based Object Tracking Using Localization Layers and Deep Features Interpolation Al-Hussein A. El-Shafie Faculty of Engineering Cairo University Giza, Egypt elshafie_a@yahoo.com Mohamed Zaki Faculty
More informationFully-Convolutional Siamese Networks for Object Tracking
Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking
More informationUnveiling the Power of Deep Tracking
Unveiling the Power of Deep Tracking Goutam Bhat 1, Joakim Johnander 1,2, Martin Danelljan 1, Fahad Shahbaz Khan 1,3, and Michael Felsberg 1 1 CVL, Department of Electrical Engineering, Linköping University,
More informationRobust Visual Tracking with Deep Convolutional Neural Network based Object Proposals on PETS
Robust Visual Tracking with Deep Convolutional Neural Network based Object Proposals on PETS Gao Zhu Fatih Porikli,2,3 Hongdong Li,3 Australian National University, NICTA 2 ARC Centre of Excellence for
More informationObject-Aware Tracking
Object-Aware Tracking Ivan Bogun Eraldo Ribeiro Department of Computer Sciences Florida Institute of Technology, Melbourne, Florida, U.S.A. ibogun21@my.fit.edu, eribeiro@cs.fit.edu Abstract In this paper,
More informationReal-Time MDNet. 1 Introduction. Ilchae Jung 1, Jeany Son 1, Mooyeol Baek 1, and Bohyung Han 2
Real-Time MDNet Ilchae Jung 1, Jeany Son 1, Mooyeol Baek 1, and Bohyung Han 2 1 Dept. of CSE, POSTECH, Korea 2 Dept. of ECE & ASRI, Seoul National University, Korea {chey0313,jeany,mooyeol}@postech.ac.kr
More informationLearning to Track at 100 FPS with Deep Regression Networks - Supplementary Material
Learning to Track at 1 FPS with Deep Regression Networks - Supplementary Material David Held, Sebastian Thrun, Silvio Savarese Department of Computer Science Stanford University {davheld,thrun,ssilvio}@cs.stanford.edu
More informationVISUAL object tracking is one of the fundamental problems
Robust Visual Tracking via Hierarchical Convolutional Features Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang arxiv:77.386v [cs.cv] 2 Jul 27 Abstract Visual tracking is challenging as target
More informationVISUAL object tracking is one of the fundamental problems
Robust Visual Tracking via Hierarchical Convolutional Features Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang arxiv:77.386v2 [cs.cv] Aug 28 Abstract Visual tracking is challenging as target
More informationarxiv: v1 [cs.cv] 10 Nov 2017 Abstract
UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking Zheng Zhu Guan Huang, Wei Zou Dalong Du, Chang Huang Institute of Automation, Chinese Academy of Sciences University of Chinese
More informationVisual Tracking via Spatially Aligned Correlation Filters Network
Visual Tracking via Spatially Aligned Correlation Filters Network Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, and Steve Maybank 2 CAS Center for Excellence in Brain Science
More informationEnd-to-end Flow Correlation Tracking with Spatial-temporal Attention
End-to-end Flow Correlation Tracking with Spatial-temporal Attention Zheng Zhu 1,2, Wei Wu 3, Wei Zou 1,2,4, Junjie Yan 3 1 Institute of Automation, Chinese Academy of Sciences, Beijing, China 2 University
More informationVisual Object Tracking. Jianan Wu Megvii (Face++) Researcher Dec 2017
Visual Object Tracking Jianan Wu Megvii (Face++) Researcher wjn@megvii.com Dec 2017 Applications From image to video: Augmented Reality Motion Capture Surveillance Sports Analysis Wait. What is visual
More informationarxiv: v1 [cs.cv] 2 Sep 2018
Natural Language Person Search Using Deep Reinforcement Learning Ankit Shah Language Technologies Institute Carnegie Mellon University aps1@andrew.cmu.edu Tyler Vuong Electrical and Computer Engineering
More informationFully-Convolutional Siamese Networks for Object Tracking
Fully-Convolutional Siamese Networks for Object Tracking Luca Bertinetto*, Jack Valmadre*, João Henriques, Andrea Vedaldi and Philip Torr www.robots.ox.ac.uk/~luca luca.bertinetto@eng.ox.ac.uk Tracking
More informationSupplementary file for Robust Visual Tracking Using Oblique Random Forests
Supplementary file for Robust Visual Tracking Using Oblique Random Forests Le Zhang ADSC Singapore 38632 zhang.le@adsc.com.sg Jagannadan Varadarajan ADSC Singapore 38632 vjagan@adsc.com.sg Pierre Moulin
More informationarxiv: v1 [cs.cv] 5 Sep 2018
arxiv:1809.01368v1 [cs.cv] 5 Sep 2018 Towards a Better Match in Siamese Network Based Visual Object Tracker Anfeng He 1, Chong Luo 2, Xinmei Tian 1, and Wenjun Zeng 2 1 CAS Key Laboratory of Technology
More informationRoI Pooling Based Fast Multi-Domain Convolutional Neural Networks for Visual Tracking
Advances in Intelligent Systems Research, volume 133 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE2016) RoI Pooling Based Fast Multi-Domain Convolutional Neural
More informationConvolutional Features for Correlation Filter Based Visual Tracking
Convolutional Features for Correlation Filter Based Visual Tracking Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan, Michael Felsberg Computer Vision Laboratory, Linköping University, Sweden {martin.danelljan,
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 informationVISUAL tracking is a fundamental problem in computer
.9/TPAMI.28.282887, IEEE Transactions on Pattern Analysis and Machine Intelligence IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Hedging Deep Features for Visual Tracking Yuankai Qi, Shengping
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 informationarxiv: v2 [cs.cv] 8 Jan 2019
Deeper and Wider Siamese Networks for Real-Time Visual Tracking arxiv:90.0660v2 [cs.cv] Jan 209 Zhipeng Zhang NLPR, CASIA zhangzhipeng20@ia.ac.cn Abstract Siamese networks have drawn great attention in
More informationGIVEN an initial state (or bounding box) of a target
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 26, NO. 8, AUGUST 2017 3817 Locator-Checker-Scaler Object Tracking Using Spatially Ordered and Weighted Patch Descriptor Han-Ul Kim, Student Member, IEEE, and
More informationDeep Learning in Visual Recognition. Thanks Da Zhang for the slides
Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object
More informationarxiv: v1 [cs.cv] 21 Nov 2016
SANet: Structure-Aware Network for Visual Tracking Heng Fan and Haibin Ling Department of Computer and Information Sciences, Temple University, Philadelphia, USA {hengfan, hbling}@temple.edu arxiv:6.06878v
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 informationarxiv: v2 [cs.cv] 13 Sep 2017
Learning Policies for Adaptive Tracking with Deep Feature Cascades Chen Huang Simon Lucey Deva Ramanan Robotics Institute, Carnegie Mellon University chenh2@andrew.cmu.edu {slucey,deva}@cs.cmu.edu arxiv:178.2973v2
More informationarxiv: v2 [cs.cv] 8 Nov 2018
Learning a Robust Society of Tracking Parts using Co-occurrence Constraints Elena Burceanu 1,2,3 and Marius Leordeanu 1,2,4 arxiv:1804.01771v2 [cs.cv] 8 Nov 2018 1 Bitdefender, Romania eburceanu@bitdefender.com
More informationVisual Tracking UCU Day 3: State-of-art methods Dmytro Mishkin. Center for Machine Perception Czech Technical University in Prague
Visual Tracking course @ UCU Day 3: State-of-art methods Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague Lviv, Ukraine 2017 Heavily based on tutorial: Visual Tracking
More informationA Twofold Siamese Network for Real-Time Object Tracking
A Twofold Siamese Network for Real-Time Object Tracking Anfeng He, Chong Luo, Xinmei Tian, and Wenjun Zeng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System,
More informationStructured Siamese Network for Real-Time Visual Tracking
Structured Siamese Network for Real-Time Visual Tracking Yunhua Zhang [ 3 3567 25X], Lijun Wang [ 3 2538 8358], Jinqing Qi [ 2 3777 245], Dong Wang [ 2 6976 44], Mengyang Feng [ 2 72 4655], and Huchuan
More informationLearning Dynamic Memory Networks for Object Tracking
Learning Dynamic Memory Networks for Object Tracking Tianyu Yang [ 2 9674 522] and Antoni B. Chan [ 2 2886 253] Department of Computer Science, City University of Hong Kong, Hong Kong, China tianyyang8-c@my.cityu.edu.hk,
More informationVISUAL object tracking is an established yet rapidly. When Correlation Filters Meet Siamese Networks for Real-time Complementary Tracking
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI.9/TCSVT.29.2892759,
More informationMulti-task Correlation Particle Filter for Robust Object Tracking
Multi-tas Correlation Particle Filter for Robust Object Tracing Tianzhu Zhang 1,2 Changsheng Xu 1,2 Ming-Hsuan Yang 3 1 National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy
More informationOnline Learning of Discriminative Correlation Filter Bank for Visual Tracking
information Article Online Learning of Discriminative Correlation Filter Bank for Visual Tracking Jian Wei ID and Feng Liu * Jiangsu Province Key Lab on Image Processing and Image Communications, Nanjing
More informationA Benchmark and Simulator for UAV Tracking -Supplementary Material-
A Benchmark and Simulator for UAV Tracking -Supplementary Material- Matthias Mueller, Neil Smith, and Bernard Ghanem King Abdullah University of Science and Technology (KAUST), Saudi Arabia {matthias.mueller.2,
More informationSANet: Structure-Aware Network for Visual Tracking
SANet: Structure-Aware Network for Visual Tracking Heng Fan Haibin Ling Department of Computer and Information Sciences, Temple University, Philadelphia, USA 2 HiScene Information Technologies, Shanghai,
More informationECO: Efficient Convolution Operators for Tracking
ECO: Efficient Convolution Operators for Tracking Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg Computer Vision Laboratory, Department of Electrical Engineering, Linköping University,
More informationRobust Tracking using Manifold Convolutional Neural Networks with Laplacian Regularization
IEEE TRANSACTIONS ON MULTIMEDIA 1 Robust Tracking using Manifold Convolutional Neural Networks with Laplacian Regularization Hongwei Hu, Bo Ma, Member, IEEE, Jianbing Shen, Senior Member, IEEE, Hanqiu
More informationCorrelation Filters with Weighted Convolution Responses
Correlation Filters with Weighted Convolution Responses Zhiqun He 1, Yingruo Fan 1, Junfei Zhuang 1, Yuan Dong 1,2, HongLiang Bai 2 1 Beijing University of Posts and Telecommunications, 2 Beijing FaceAll
More informationarxiv: v1 [cs.cv] 26 Nov 2017
MAVOT: Memory-Augmented Video Object Tracking Boyu Liu Yanzhao Wang HKUST {bliuag,ywangdg}@connect.ust.hk Yu-Wing Tai Tencent Youtu yuwingtai@tencent.com Chi-Keung Tang HKUST cktang@cs.ust.hk arxiv:1711.09414v1
More informationarxiv: v1 [cs.cv] 28 Nov 2017
Tracking for Half an Hour Ran Tao, Efstratios Gavves, Arnold W.M. Smeulders QUVA Lab, University of Amsterdam arxiv:1711.10217v1 [cs.cv] 28 Nov 2017 Abstract Long-term tracking requires extreme stability
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 informationBeyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking Martin Danelljan, Andreas Robinson, Fahad Shahbaz Khan, Michael Felsberg CVL, Department of Electrical Engineering,
More informationarxiv: v2 [cs.cv] 10 Apr 2017
ECO: Efficient Convolution Operators for Tracking Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg Computer Vision Laboratory, Department of Electrical Engineering, Linko ping University,
More informationarxiv: v2 [cs.cv] 14 Jan 2019
FuCoLoT A Fully-Correlational Long-Term Tracker Alan Lukežič 1, Luka Čehovin Zajc1, Tomáš Vojíř 2, Jiří Matas 2, and Matej Kristan 1 arxiv:1711.09594v2 [cs.cv] 14 Jan 2019 1 Faculty of Computer and Information
More informationDeep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.
Visualizing and Understanding Convolutional Networks Christopher Pennsylvania State University February 23, 2015 Some Slide Information taken from Pierre Sermanet (Google) presentation on and Computer
More informationSynthetic data generation for end-to-end thermal infrared tracking
SUBMITTED TO IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Synthetic data generation for end-to-end thermal infrared tracking Lichao Zhang, Abel Gonzalez-Garcia, Joost van de Weijer, Martin Danelljan, and Fahad
More informationRobust visual tracking by exploiting the historical tracker snapshots
Robust visual tracking by exploiting the historical tracker snapshots Jiatong Li,2, Zhibin Hong 2, and Baojun Zhao School of Information and Electronics, Beijing Institute of Technology 5 South Zhongguancun
More informationarxiv: v1 [cs.cv] 7 Sep 2018
DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking Mohamed H. Abdelpakey 1 ( ), Mohamed S. Shehata 1, and Mostafa M. Mohamed 2 arxiv:1809.02714v1 cs.cv] 7 Sep 2018
More informationAdaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
International Journal of Computer Vision manuscript No. (will be inserted by the editor) Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking Chao Ma Jia-Bin Huang Xiaokang
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 informationOnline Multi-Face Detection and Tracking using Detector Confidence and Structured SVMs
Online Multi-Face Detection and Tracking using Detector Confidence and Structured SVMs Francesco Comaschi 1, Sander Stuijk 1, Twan Basten 1,2 and Henk Corporaal 1 1 Eindhoven University of Technology,
More informationSupplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Kihyuk Sohn 1 Sifei Liu 2 Guangyu Zhong 3 Xiang Yu 1 Ming-Hsuan Yang 2 Manmohan Chandraker 1,4 1 NEC Labs
More informationAutomatic detection of books based on Faster R-CNN
Automatic detection of books based on Faster R-CNN Beibei Zhu, Xiaoyu Wu, Lei Yang, Yinghua Shen School of Information Engineering, Communication University of China Beijing, China e-mail: zhubeibei@cuc.edu.cn,
More informationFine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task
Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Kyunghee Kim Stanford University 353 Serra Mall Stanford, CA 94305 kyunghee.kim@stanford.edu Abstract We use a
More informationDiscriminative Correlation Filter with Channel and Spatial Reliability (CSR-DCF)
Discriminative Correlation Filter with Channel and Spatial Reliability (CSR-DCF) Alan Lukežič 1, Andrej Muhič 1, Tomáš Vojíř 2, Luka Čehovin 1, Jiří Matas 2, Matej Kristan 1 1 Faculty of Computer and Information
More informationVISUAL tracking plays an important role in signal processing
IEEE TRANSACTIONS ON CYBERNETICS 1 Correlation Filter Learning Toward Peak Strength for Visual Tracking Yao Sui, Guanghui Wang, and Li Zhang Abstract This paper presents a novel visual tracking approach
More informationRegionlet Object Detector with Hand-crafted and CNN Feature
Regionlet Object Detector with Hand-crafted and CNN Feature Xiaoyu Wang Research Xiaoyu Wang Research Ming Yang Horizon Robotics Shenghuo Zhu Alibaba Group Yuanqing Lin Baidu Overview of this section Regionlet
More informationROBUST ONLINE FACE TRACKING-BY-DETECTION. {f.comaschi, s.stuijk, a.a.basten,
ROBUST ONLINE FACE TRACKING-BY-DETECTION Francesco Comaschi 1, Sander Stuijk 1, Twan Basten 1,2, Henk Corporaal 1 1 Eindhoven University of Technology, The Netherlands 2 TNO Embedded Systems Innovation,
More informationThe Visual Object Tracking VOT2015: Challenge and results
The Visual Object Tracking VOT2015: Challenge and results Matej Kristan, Aleš Leonardis, Jiri Matas, Michael Felsberg Luka Čehovin, Gustavo Fernandez, Tomaš Vojir, Georg Nebehay, Roman Pflugfelder, et
More informationDeepIndex for Accurate and Efficient Image Retrieval
DeepIndex for Accurate and Efficient Image Retrieval Yu Liu, Yanming Guo, Song Wu, Michael S. Lew Media Lab, Leiden Institute of Advance Computer Science Outline Motivation Proposed Approach Results Conclusions
More informationCollaborative Correlation Tracking
ZHU, WANG, WU, LU: COLLABORATIVE CORRELATION TRACKING 1 Collaborative Correlation Tracking Guibo Zhu 1 gbzhu@nlpr.ia.ac.cn Jinqiao Wang 1 jqwang@nlpr.ia.ac.cn Yi Wu 2 ywu.china@yahoo.com Hanqing Lu 1 luhq@nlpr.ia.ac.cn
More informationIntegrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation
Integrating Boundary and Center Correlation Filters for Visual Tracing with Aspect Ratio Variation Feng Li, Yingjie Yao, Peihua Li 2, David Zhang 3, Wangmeng Zuo,, and Ming-Hsuan Yang 4 School of Computer
More informationEvaluation of Visual Object Trackers on Equirectangular Panorama
Evaluation of Visual Object Trackers on Equirectangular Panorama Ugur Kart, Joni-Kristian Kämäräinen, Lixin Fan 2 and Moncef Gabbouj Laboratory of Signal Processing, Tampere University of Technology, Finland
More informationA New Approach for Train Driver Tracking in Real Time. Ming-yu WANG, Si-le WANG, Li-ping CHEN, Xiang-yang CHEN, Zhen-chao CUI, Wen-zhu YANG *
2018 International Conference on Modeling, Simulation and Analysis (ICMSA 2018) ISBN: 978-1-60595-544-5 A New Approach for Train Driver Tracking in Real Time Ming-yu WANG, Si-le WANG, Li-ping CHEN, Xiang-yang
More informationKernalised Multi-resolution Convnet for Visual Tracking
Kernalised Multi-resolution Convnet for Visual Tracking Di Wu, Wenbin Zou, Xia Li Shenzhen University dwu, wzou, lixia@szu.edu.cn Yong Zhao Peking University Shenzhen Graduate School yongzhao@pkusz.edu.cn
More informationParallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking Heng Fan Haibin Ling Meitu HiScene Lab, HiScene Information Technologies, Shanghai, China Department of Computer
More informationarxiv: v1 [cs.cv] 30 Sep 2015
Online Object Tracking with Proposal Selection Yang Hua Karteek Alahari Cordelia Schmid Inria arxiv:1509.09114v1 [cs.cv] 30 Sep 2015 Abstract Tracking-by-detection approaches are some of the most successful
More informationSUBMISSION TO IEEE TRANSACTIONS ON IMAGE PROCESSING 1. RGB-T Object Tracking: Benchmark and Baseline
SUBMISSION TO IEEE TRANSACTIONS ON IMAGE PROCESSING 1 RGB-T Object Tracking: Benchmark and Baseline Chenglong Li, Xinyan Liang, Yijuan Lu, Nan Zhao, and Jin Tang arxiv:1805.08982v1 [cs.cv] 23 May 2018
More informationLarge-scale gesture recognition based on Multimodal data with C3D and TSN
Large-scale gesture recognition based on Multimodal data with C3D and TSN July 6, 2017 1 Team details Team name ASU Team leader name Yunan Li Team leader address, phone number and email address: Xidian
More informationThe Visual Object Tracking VOT2015 challenge results
2015 IEEE International Conference on Computer Vision Workshops The Visual Object Tracking VOT2015 challenge results Matej Kristan 1, Jiri Matas 2, Aleš Leonardis 3, Michael Felsberg 4, Luka Čehovin 1,
More informationDeep Face Recognition. Nathan Sun
Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an
More informationarxiv: v2 [cs.cv] 10 Apr 2017
Deep Reinforcement Learning for Visual Object Tracking in Videos Da Zhang 1, Hamid Maei 2, Xin Wang 1, and Yuan-Fang Wang 1 arxiv:1701.08936v2 [cs.cv] 10 Apr 2017 1 Department of Computer Science, University
More informationVISUAL object tracking confronts with major challenges. Not All Negatives are Equal: Learning to Track with Multiple Background Clusters
IEEE TRANSACTION ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY Not All Negatives are Equal: Learning to Track with Multiple Background Clusters Gao Zhu, Student Member, IEEE, Fatih Porikli, Fellow, IEEE,
More informationDiscriminative Correlation Filter with Channel and Spatial Reliability
Discriminative Correlation Filter with Channel and Spatial Reliability Alan Lukežič 1, Tomáš Vojíř 2, Luka Čehovin Zajc 1, Jiří Matas 2 and Matej Kristan 1 1 Faculty of Computer and Information Science,
More informationRobust UAV-based Tracking Using Hybrid Classifiers
Robust UAV-based Tracking Using Hybrid Classifiers Yong Wang University of Ottawa 75 Laurier Ave E, Ottawa, ON K1N 6N5 ywang6@uottawa.ca Wei Shi INSKY Lab, Leotail Intelligent Tech 1628, Pudong District,
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 information[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors
[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors Junhyug Noh Soochan Lee Beomsu Kim Gunhee Kim Department of Computer Science and Engineering
More informationThe Visual Object Tracking VOT2016 challenge results
1 The Visual Object Tracking VOT2016 challenge results Matej Kristan 1, Aleš Leonardis 2, Jiři Matas 3, Michael Felsberg 4, Roman Pflugfelder 5, Luka Čehovin1, Tomáš Vojí r 3, Gustav Häger 4, Alan Lukežič
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 informationA multi-view model for visual tracking via correlation filters
A multi-view model for visual tracking via correlation filters Xin Li a,, Qiao Liu a,, Zhenyu He a,, Hongpeng Wang a, Chunkai Zhang a, Wen-Sheng Chen b a School of Computer Science, Harbin Institute of
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous
More informationTwo-Stream Convolutional Networks for Action Recognition in Videos
Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan Andrew Zisserman Cemil Zalluhoğlu Introduction Aim Extend deep Convolution Networks to action recognition in video. Motivation
More informationSupplementary Material: Unconstrained Salient Object Detection via Proposal Subset Optimization
Supplementary Material: Unconstrained Salient Object via Proposal Subset Optimization 1. Proof of the Submodularity According to Eqns. 10-12 in our paper, the objective function of the proposed optimization
More informationA Survey on Visual Object Tracking: Datasets, Methods and Metrics
A Survey on Visual Object Tracking: Datasets, Methods and Metrics V. Ramalakshmi @ Kanthimathi 1, Dr. M. Germanus Alex 2 1 Research Scholar, Department of Computer Science, Bharathiar University, Coimbatore,
More informationDirect Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab.
[ICIP 2017] Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab., POSTECH Pedestrian Detection Goal To draw bounding boxes that
More informationMeta-path based Multi-Network Collective Link Prediction
Meta-path based Multi-Network Collective Link Prediction Jiawei Zhang 1,2, Philip S. Yu 1, Zhi-Hua Zhou 2 University of Illinois at Chicago 2, Nanjing University 2 Traditional social link prediction in
More informationArtificial Intelligence. Programming Styles
Artificial Intelligence Intro to Machine Learning Programming Styles Standard CS: Explicitly program computer to do something Early AI: Derive a problem description (state) and use general algorithms to
More informationDeep-LK for Efficient Adaptive Object Tracking
Deep-LK for Efficient Adaptive Object Tracking Chaoyang Wang, Hamed Kiani Galoogahi, Chen-Hsuan Lin, and Simon Lucey 1 Abstract In this paper, we present a new approach for efficient regression-based object
More informationBeyond standard benchmarks: Parameterizing performance evaluation in visual object tracking
Beyond standard benchmarks: Parameterizing performance evaluation in visual object tracking Luka Čehovin Zajc, Alan Lukežič, Aleš Leonardis, Matej Kristan University of Ljubljana Faculty of computer and
More informationVISUAL object tracking is an important problem in
IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 19, NO. 4, APRIL 017 763 Occlusion-Aware Real-Time Object Tracking Xingping Dong, Jianbing Shen, Senior Member, IEEE, Dajiang Yu, Wenguan Wang, Jianhong Liu, and Hua
More informationMulti-View 3D Object Detection Network for Autonomous Driving
Multi-View 3D Object Detection Network for Autonomous Driving Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia CVPR 2017 (Spotlight) Presented By: Jason Ku Overview Motivation Dataset Network Architecture
More information