Recent Advances in Computer Vision

A
Recent Advances in Computer Vision

         Ming-Hsuan Yang
Computer vision
• Holly grail – tell a story from an image
History
• “In the 1960s, almost no one realized that
  machine vision was difficult.” – David Marr,
  1982
• Marvin Minsky asked Gerald Jay Sussman
  to “spend the summer linking a camera to
  a computer and getting the computer to
  describe what it saw” – Crevier, 1993
• 40+ years later, we are still working on this
1970s
1980s
1990s


        • Face detection
        • Particle filter
        • Pfinder
        • Normalized cut
2000s
• SIFT
  –   Mosaicing, panorama
  –   Object recognition
  –   Photo tourism, photosynth
  –   Human detection

• Adaboost-based face detector
Related topics
Conferences
• CVPR – Computer Vision and Pattern
  Recognition, since 1983
  – Annual, held in US
• ICCV – International Conference on
  Computer Vision, since 1987
  – Every other year, alternate in 3 continents
• ECCV – European Conference on
  Computer Vision, since 1990
  – Every other year, held in Europe
Conferences (cont’d)
• ACCV – Asian Conference on Computer
  Vision
• BMVC – British Machine Vision
  Conference
• ICPR – International Conference on
  Pattern Recognition
• SIGGRAPH
• NIPS – Neural Information Processing
  Systems
Conferences (cont’d)
• MICCAI – Medical Image Computing and
  Computer-Assisted Intervention
• ISBI – International Symposium on Biomedical
  Imaging
• FG – IEEE Conference on Automatic Face and
  Gesture Recognition
• ICCP, ICDR, ICVS, DAGM, CAIP, MVA, AAAI,
  IJCAI, ICML, ICRA, ICASSP, ICIP, SPIE, DCC,
  WACV, 3DPVT, ACM Multimedia, ICME, …
Conference organization
• General chairs: administration
• Program chairs: handling papers
• Area chairs:
  –   Assign reviewers
  –   Read reviews and rebuttals
  –   Consolidation reports
  –   Recommendation
• Reviewers
• Authors
Review process
• Submission
• CVPR/ECCV/ICCV
  – Double blind review
  – Program chairs: assign papers to area chairs
  – Area chairs: assign papers to reviewers
• Rebuttal
Area chair meetings
• 2 day meetings
• Several panels
• Each paper is reviewed by at least 2 area
  chairs
• Buddy system
• Area chair make recommendations
• Program chairs make final decisions
Conference acceptance rates
•   ICCV/CVPR/ECCV: ~ 30%
•   ACCV (2009): ~ 30%
•   NIPS: ~ 30%
•   BMVC: ~ 40%
•   ICIP: ~ 45%
•   ICPR: ~ 55%

• Disclaimer
    – low acceptance rate = high quality?
CVPR
 Submission             Oral




              Overall
ICCV
 Submission             Oral




              Overall
ECCV
 Submission             Oral




              Overall
Journals
• PAMI – IEEE Transactions on Pattern
  Analysis and Machine Intelligence, since
  1979 (impact factor: 5.96, #1 in all engineering
  and AI, top-ranked IEEE and CS journal)
• IJCV – International Journal on Computer
  Vision, since 1988 (impact factor: 5.36, #2 in
  all engineering and AI)
• CVIU – Computer Vision and Image
  Understanding, since 1972 (impact factor:
  2.20)
Journals (cont’d)
• IVC – Image and Vision Computing
• IEEE Transactions on Medical Imaging
• TIP – IEEE Transactions on Image
  Processing
• MVA – Machine Vision and Applications
• PR – Pattern Recognition
• TM – IEEE Transactions on Multimedia
• …
PAMI review process
• Editor-in-chief (EIC) assigns papers to
  associate editors (AE)
• AE assigns reviewers
• First-round review: 3-6 months
  –   Accept as is
  –   Accept with minor revision
  –   Major revision
  –   Resubmit as new
  –   Reject
PAMI review process (cont’d)
• Second-round review: 2-4 months
  – Accept as is
  – Accept with minor revision
  – Reject
• EIC makes final decision
• Overall turn-around time: 6 to 12 months
• Rule of thumb: 30% additional work
  beyond a CVPR/ICCV/ECCV paper
IJCV/CVIU review process
• Similar formats
• CVIU has roughly the same turn-around
  time as PAMI
• IJCV tends to have longer turn-around
  time
Journal acceptance rate
• PAMI, IJCV: ~ 30%
• CVIU: ~ 30%
Tools
• Google scholar, citeseer,
• h-index
• Software: publish or perish

• Disclaimer:
  – h index = significance?
  – # of citation = significance
How to get your papers rejected?
• Refer to Jim Kajia (SIGGRAPH 93 papers
  chair): How to get your SIGGRAPH paper
  rejected?
• Do not
  –   Pay attention to review process
  –   Put yourself as a reviewer perspective
  –   Put the work in right context
  –   Carry out sufficient amount of experiments
  –   Compare with state-of-the-art algorithms
  –   Pay attention to writing
Pay attention to review process
• Learn how others/you can pick apart a
  paper
• Learn from other’s mistakes
• Learn how to write good papers
• Learn what it takes to get a paper
  published
Put yourself as reviewer
•   What are the contributions?
•   Does it advance the science in the filed?
•   Why you should accept this paper?
•   Is this paper a case study?
•   Is this paper interesting?
•   What is the audience?
•   Does anyone care about this work?
Experimental validation
•   Common data set
•   Killer data set
•   Large scale experiment
•   Evaluation metric
Compare with state of the art
• Do your homework
• Need to know what is out there
• Need to show why one’s method
  outperforms others, and in what way?
  – speed?
  – accuracy?
  – easy to implement?
  – general application?
Writing
•   Clear presentation
•   Terse
•   Careful about wording
•   Make claims with strong evidence
Review form
• Summary
• Overall Rating
  – Definite accept, weakly accept, borderline, weakly reject, definite
    reject
• Novelty
  – Very original, original, minor originality, has been done before
• Importance/relevance
  – Of broad interest, interesting to a subarea, interesting only to a
    small number of attendees, out of CVPR scope
Review form (cont’d)
• Clarity of presentation
   – Reads very well, is clear enough, difficult to read, unreadable
• Technical correctness
   – Definite correct, probably correct but did not check completely,
     contains rectifiable errors, has major problems
• Experimental validation
   – Excellent validation or N/A (a theoretical paper), limited but
     convincing, lacking in some aspects, insufficient validation
• Additional comments
• Reviewer’s name
Challenging issues
•   Large scale
•   Unconstrained
•   Real-time
•   Robustness
•   Recover from failure – graceful dead
Some hot topics
•   Object recognition, categorization
•   Internet scale image search
•   Video search
•   Human detection
•   3D human pose estimation
•   Computational photography
•   Scene understanding
Some hot tools
•   Prior
•   Context
•   Sparse representation
•   Multiple instance learning
•   Online learning
•   Convex optimization
•   Constraint
•   Hashing
Prior




        Torralba and Sinha ICCV 01
Prior




        Heitz and Koller ECCV 08
Prior




   Jia CVPR 08   He et al. CVPR 09
Scene understanding




          Leibe et al. CVPR 07
Image search




          Wu et al. CVPR 09
Computational photography




        Johnson and Adelson et al. CVPR 09
Computational photography




           Ahuja et al.
1 of 43

Recommended

Apache Calcite overview by
Apache Calcite overviewApache Calcite overview
Apache Calcite overviewJulian Hyde
19.5K views9 slides
深層学習フレームワークChainerの特徴 by
深層学習フレームワークChainerの特徴深層学習フレームワークChainerの特徴
深層学習フレームワークChainerの特徴Yuya Unno
59.4K views46 slides
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia... by
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...Deep Learning JP
720 views42 slides
Introduction to Apache Calcite by
Introduction to Apache CalciteIntroduction to Apache Calcite
Introduction to Apache CalciteJordan Halterman
16.3K views109 slides
Spark MLlibではじめるスケーラブルな機械学習 by
Spark MLlibではじめるスケーラブルな機械学習Spark MLlibではじめるスケーラブルな機械学習
Spark MLlibではじめるスケーラブルな機械学習NTT DATA OSS Professional Services
37.2K views51 slides
金融時系列のための深層t過程回帰モデル by
金融時系列のための深層t過程回帰モデル金融時系列のための深層t過程回帰モデル
金融時系列のための深層t過程回帰モデルKei Nakagawa
2K views20 slides

More Related Content

What's hot

Rethinking State Management in Cloud-Native Streaming Systems by
Rethinking State Management in Cloud-Native Streaming SystemsRethinking State Management in Cloud-Native Streaming Systems
Rethinking State Management in Cloud-Native Streaming SystemsYingjun Wu
413 views95 slides
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料) by
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)NTT DATA OSS Professional Services
53K views60 slides
t-SNE by
t-SNEt-SNE
t-SNE貴之 八木
16.7K views32 slides
Elasticsearchインデクシングのパフォーマンスを測ってみた by
Elasticsearchインデクシングのパフォーマンスを測ってみたElasticsearchインデクシングのパフォーマンスを測ってみた
Elasticsearchインデクシングのパフォーマンスを測ってみたRyoji Kurosawa
7.4K views31 slides
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf... by
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...ddnpaa
687 views26 slides
数理最適化と機械学習の 融合アプローチ -分類と新しい枠組み- by
数理最適化と機械学習の融合アプローチ-分類と新しい枠組み-数理最適化と機械学習の融合アプローチ-分類と新しい枠組み-
数理最適化と機械学習の 融合アプローチ -分類と新しい枠組み-MIKIOKUBO3
823 views42 slides

What's hot(20)

Rethinking State Management in Cloud-Native Streaming Systems by Yingjun Wu
Rethinking State Management in Cloud-Native Streaming SystemsRethinking State Management in Cloud-Native Streaming Systems
Rethinking State Management in Cloud-Native Streaming Systems
Yingjun Wu413 views
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料) by NTT DATA OSS Professional Services
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)
Apache Sparkに手を出してヤケドしないための基本 ~「Apache Spark入門より」~ (デブサミ 2016 講演資料)
Elasticsearchインデクシングのパフォーマンスを測ってみた by Ryoji Kurosawa
Elasticsearchインデクシングのパフォーマンスを測ってみたElasticsearchインデクシングのパフォーマンスを測ってみた
Elasticsearchインデクシングのパフォーマンスを測ってみた
Ryoji Kurosawa7.4K views
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf... by ddnpaa
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...
ddnpaa 687 views
数理最適化と機械学習の 融合アプローチ -分類と新しい枠組み- by MIKIOKUBO3
数理最適化と機械学習の融合アプローチ-分類と新しい枠組み-数理最適化と機械学習の融合アプローチ-分類と新しい枠組み-
数理最適化と機械学習の 融合アプローチ -分類と新しい枠組み-
MIKIOKUBO3823 views
Word embeddings by Shruti kar
Word embeddingsWord embeddings
Word embeddings
Shruti kar158 views
AWS Redshift Analyzeの必要性とvacuumの落とし穴 by Moto Fukao
AWS Redshift Analyzeの必要性とvacuumの落とし穴AWS Redshift Analyzeの必要性とvacuumの落とし穴
AWS Redshift Analyzeの必要性とvacuumの落とし穴
Moto Fukao7.4K views
Deep Dive into Hyperparameter Tuning by Shubhmay Potdar
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter Tuning
Shubhmay Potdar629 views
20170714_MySQL 5.7 GIS(地理情報システム) by 日本オラクル株式会社 MySQL GBU 山﨑由章 by Insight Technology, Inc.
20170714_MySQL 5.7 GIS(地理情報システム) by 日本オラクル株式会社 MySQL GBU 山﨑由章20170714_MySQL 5.7 GIS(地理情報システム) by 日本オラクル株式会社 MySQL GBU 山﨑由章
20170714_MySQL 5.7 GIS(地理情報システム) by 日本オラクル株式会社 MySQL GBU 山﨑由章
Optuna: A Define-by-Run Hyperparameter Optimization Framework by Preferred Networks
Optuna: A Define-by-Run Hyperparameter Optimization FrameworkOptuna: A Define-by-Run Hyperparameter Optimization Framework
Optuna: A Define-by-Run Hyperparameter Optimization Framework
SQL on everything, in memory by Julian Hyde
SQL on everything, in memorySQL on everything, in memory
SQL on everything, in memory
Julian Hyde7.4K views
多変量解析の一般化 by Akisato Kimura
多変量解析の一般化多変量解析の一般化
多変量解析の一般化
Akisato Kimura3.1K views
분산 강화학습 논문(DeepMind IMPALA) 구현 by 정주 김
분산 강화학습 논문(DeepMind IMPALA) 구현분산 강화학습 논문(DeepMind IMPALA) 구현
분산 강화학습 논문(DeepMind IMPALA) 구현
정주 김4.7K views
Apache Calcite: One Frontend to Rule Them All by Michael Mior
Apache Calcite: One Frontend to Rule Them AllApache Calcite: One Frontend to Rule Them All
Apache Calcite: One Frontend to Rule Them All
Michael Mior676 views
Available methods for predicting materials synthesizability using computation... by Anubhav Jain
Available methods for predicting materials synthesizability using computation...Available methods for predicting materials synthesizability using computation...
Available methods for predicting materials synthesizability using computation...
Anubhav Jain42 views
Big Data Architecture by Guido Schmutz
Big Data ArchitectureBig Data Architecture
Big Data Architecture
Guido Schmutz25.3K views

Viewers also liked

How to come up with new research ideas by
How to come up with new research ideasHow to come up with new research ideas
How to come up with new research ideasJia-Bin Huang
13.7K views141 slides
How to Read Academic Papers by
How to Read Academic PapersHow to Read Academic Papers
How to Read Academic PapersJia-Bin Huang
7K views54 slides
Top 10 ways to get your paper rejected at #CAGJournal by
Top 10 ways to get your paper rejected at #CAGJournalTop 10 ways to get your paper rejected at #CAGJournal
Top 10 ways to get your paper rejected at #CAGJournalJoaquim Jorge
3.3K views53 slides
Computer Vision Crash Course by
Computer Vision Crash CourseComputer Vision Crash Course
Computer Vision Crash CourseJia-Bin Huang
2.7K views216 slides
Research 101 - Paper Writing with LaTeX by
Research 101 - Paper Writing with LaTeXResearch 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeXJia-Bin Huang
11.5K views47 slides
Raskar 2012, Idea Hexagon by
Raskar 2012, Idea HexagonRaskar 2012, Idea Hexagon
Raskar 2012, Idea HexagonCamera Culture Group, MIT Media Lab
10.3K views74 slides

Viewers also liked(20)

How to come up with new research ideas by Jia-Bin Huang
How to come up with new research ideasHow to come up with new research ideas
How to come up with new research ideas
Jia-Bin Huang13.7K views
How to Read Academic Papers by Jia-Bin Huang
How to Read Academic PapersHow to Read Academic Papers
How to Read Academic Papers
Jia-Bin Huang7K views
Top 10 ways to get your paper rejected at #CAGJournal by Joaquim Jorge
Top 10 ways to get your paper rejected at #CAGJournalTop 10 ways to get your paper rejected at #CAGJournal
Top 10 ways to get your paper rejected at #CAGJournal
Joaquim Jorge3.3K views
Computer Vision Crash Course by Jia-Bin Huang
Computer Vision Crash CourseComputer Vision Crash Course
Computer Vision Crash Course
Jia-Bin Huang2.7K views
Research 101 - Paper Writing with LaTeX by Jia-Bin Huang
Research 101 - Paper Writing with LaTeXResearch 101 - Paper Writing with LaTeX
Research 101 - Paper Writing with LaTeX
Jia-Bin Huang11.5K views
About DevFactory by HackerEarth
About DevFactory About DevFactory
About DevFactory
HackerEarth5.9K views
Richard Matthew Stallman - A Brief Biography by HackerEarth
Richard Matthew Stallman - A Brief BiographyRichard Matthew Stallman - A Brief Biography
Richard Matthew Stallman - A Brief Biography
HackerEarth2.2K views
Intel RealSense technology : Overview and demos by Zayen Chagra
Intel RealSense technology : Overview and demosIntel RealSense technology : Overview and demos
Intel RealSense technology : Overview and demos
Zayen Chagra1.2K views
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro... by Edge AI and Vision Alliance
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro..."Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
미래교육을 위한 인터페이스 NUI & education by Choohan Cho
미래교육을 위한 인터페이스 NUI & education미래교육을 위한 인터페이스 NUI & education
미래교육을 위한 인터페이스 NUI & education
Choohan Cho1.2K views
Computer vision, machine, and deep learning by Igi Ardiyanto
Computer vision, machine, and deep learningComputer vision, machine, and deep learning
Computer vision, machine, and deep learning
Igi Ardiyanto2.3K views
Augmented reality as next UI Challenge by Zühlke
Augmented reality as next UI ChallengeAugmented reality as next UI Challenge
Augmented reality as next UI Challenge
Zühlke1.4K views
How Computer Vision is Reshaping Real Estate Search - Andrew Flachner by Inman News
How Computer Vision is Reshaping Real Estate Search - Andrew FlachnerHow Computer Vision is Reshaping Real Estate Search - Andrew Flachner
How Computer Vision is Reshaping Real Estate Search - Andrew Flachner
Inman News546 views
How to become a Data Scientist? by HackerEarth
How to become a Data Scientist? How to become a Data Scientist?
How to become a Data Scientist?
HackerEarth11.4K views
Matrix Factorisation (and Dimensionality Reduction) by HJ van Veen
Matrix Factorisation (and Dimensionality Reduction)Matrix Factorisation (and Dimensionality Reduction)
Matrix Factorisation (and Dimensionality Reduction)
HJ van Veen5.1K views
Augment my reality info press-montreal2010 by MobileMoxie
Augment my reality info press-montreal2010Augment my reality info press-montreal2010
Augment my reality info press-montreal2010
MobileMoxie1.5K views

Similar to Recent Advances in Computer Vision

Dip by
DipDip
DipNagasuri Bala Venkateswarlu
447 views183 slides
Artifact Evaluation Experience CGO'15 / PPoPP'15 by
Artifact Evaluation Experience CGO'15 / PPoPP'15Artifact Evaluation Experience CGO'15 / PPoPP'15
Artifact Evaluation Experience CGO'15 / PPoPP'15Grigori Fursin
2.2K views17 slides
e3-chap-09.ppt by
e3-chap-09.ppte3-chap-09.ppt
e3-chap-09.pptKingSh2
6 views40 slides
Evaluation techniques by
Evaluation techniquesEvaluation techniques
Evaluation techniquesPhD Research Scholar
3.8K views40 slides
Chapter 8 Evaluation Techniques by
Chapter 8 Evaluation  TechniquesChapter 8 Evaluation  Techniques
Chapter 8 Evaluation TechniquesMLG College of Learning, Inc
117 views40 slides
Challenges in medical imaging and the VISCERAL model by
Challenges in medical imaging and the VISCERAL modelChallenges in medical imaging and the VISCERAL model
Challenges in medical imaging and the VISCERAL modelInstitute of Information Systems (HES-SO)
1.3K views23 slides

Similar to Recent Advances in Computer Vision(20)

Artifact Evaluation Experience CGO'15 / PPoPP'15 by Grigori Fursin
Artifact Evaluation Experience CGO'15 / PPoPP'15Artifact Evaluation Experience CGO'15 / PPoPP'15
Artifact Evaluation Experience CGO'15 / PPoPP'15
Grigori Fursin2.2K views
e3-chap-09.ppt by KingSh2
e3-chap-09.ppte3-chap-09.ppt
e3-chap-09.ppt
KingSh26 views
Peeking behind the test: insights and innovations from the Medical Council of... by MedCouncilCan
Peeking behind the test: insights and innovations from the Medical Council of...Peeking behind the test: insights and innovations from the Medical Council of...
Peeking behind the test: insights and innovations from the Medical Council of...
MedCouncilCan1.6K views
Operationalization of Lean thinking through Value Stream Mapping with Simulat... by Letizia Jaccheri
Operationalization of Lean thinking through Value Stream Mapping with Simulat...Operationalization of Lean thinking through Value Stream Mapping with Simulat...
Operationalization of Lean thinking through Value Stream Mapping with Simulat...
Letizia Jaccheri1.1K views
lect1.pdf by AtkaAli
lect1.pdflect1.pdf
lect1.pdf
AtkaAli4 views
Klaus Dieter Rossade online assessment by EADTU
Klaus Dieter Rossade online assessmentKlaus Dieter Rossade online assessment
Klaus Dieter Rossade online assessment
EADTU105 views
Best Practices in Recommender System Challenges by Alan Said
Best Practices in Recommender System ChallengesBest Practices in Recommender System Challenges
Best Practices in Recommender System Challenges
Alan Said6.2K views
Human computation, crowdsourcing and social: An industrial perspective by oralonso
Human computation, crowdsourcing and social: An industrial perspectiveHuman computation, crowdsourcing and social: An industrial perspective
Human computation, crowdsourcing and social: An industrial perspective
oralonso1.2K views
Usability Lab within Agile (by Ian Franklin at NUX Leeds January 2018) by Northern User Experience
Usability Lab within Agile (by Ian Franklin at NUX Leeds January 2018)Usability Lab within Agile (by Ian Franklin at NUX Leeds January 2018)
Usability Lab within Agile (by Ian Franklin at NUX Leeds January 2018)

More from antiw

Cvpr2010 open source vision software, intro and training part viii point clou... by
Cvpr2010 open source vision software, intro and training part viii point clou...Cvpr2010 open source vision software, intro and training part viii point clou...
Cvpr2010 open source vision software, intro and training part viii point clou...antiw
1.4K views54 slides
Cvpr2010 open source vision software, intro and training part vii point cloud... by
Cvpr2010 open source vision software, intro and training part vii point cloud...Cvpr2010 open source vision software, intro and training part vii point cloud...
Cvpr2010 open source vision software, intro and training part vii point cloud...antiw
995 views47 slides
graphical models for the Internet by
graphical models for the Internetgraphical models for the Internet
graphical models for the Internetantiw
2.1K views179 slides
15 pieces of advice i wish my ph d advisor had given me by
15 pieces of advice i wish my ph d advisor had given me15 pieces of advice i wish my ph d advisor had given me
15 pieces of advice i wish my ph d advisor had given meantiw
431 views24 slides
Randy pauschtimemanagement2007 by
Randy pauschtimemanagement2007Randy pauschtimemanagement2007
Randy pauschtimemanagement2007antiw
784 views96 slides
Write a research paper howto - good presentation by
Write a research paper   howto - good presentationWrite a research paper   howto - good presentation
Write a research paper howto - good presentationantiw
1.1K views46 slides

More from antiw(9)

Cvpr2010 open source vision software, intro and training part viii point clou... by antiw
Cvpr2010 open source vision software, intro and training part viii point clou...Cvpr2010 open source vision software, intro and training part viii point clou...
Cvpr2010 open source vision software, intro and training part viii point clou...
antiw1.4K views
Cvpr2010 open source vision software, intro and training part vii point cloud... by antiw
Cvpr2010 open source vision software, intro and training part vii point cloud...Cvpr2010 open source vision software, intro and training part vii point cloud...
Cvpr2010 open source vision software, intro and training part vii point cloud...
antiw995 views
graphical models for the Internet by antiw
graphical models for the Internetgraphical models for the Internet
graphical models for the Internet
antiw2.1K views
15 pieces of advice i wish my ph d advisor had given me by antiw
15 pieces of advice i wish my ph d advisor had given me15 pieces of advice i wish my ph d advisor had given me
15 pieces of advice i wish my ph d advisor had given me
antiw431 views
Randy pauschtimemanagement2007 by antiw
Randy pauschtimemanagement2007Randy pauschtimemanagement2007
Randy pauschtimemanagement2007
antiw784 views
Write a research paper howto - good presentation by antiw
Write a research paper   howto - good presentationWrite a research paper   howto - good presentation
Write a research paper howto - good presentation
antiw1.1K views
15 pieces of advice i wish my ph d advisor had given me by antiw
15 pieces of advice i wish my ph d advisor had given me15 pieces of advice i wish my ph d advisor had given me
15 pieces of advice i wish my ph d advisor had given me
antiw172 views
Note beamer by antiw
Note beamerNote beamer
Note beamer
antiw1.1K views
Open Cv 2005 Q4 Tutorial by antiw
Open Cv 2005 Q4 TutorialOpen Cv 2005 Q4 Tutorial
Open Cv 2005 Q4 Tutorial
antiw3.2K views

Recently uploaded

Gross Anatomy of the Liver by
Gross Anatomy of the LiverGross Anatomy of the Liver
Gross Anatomy of the Liverobaje godwin sunday
267 views12 slides
BUSINESS ETHICS MODULE 1 UNIT I_A.pdf by
BUSINESS ETHICS MODULE 1 UNIT I_A.pdfBUSINESS ETHICS MODULE 1 UNIT I_A.pdf
BUSINESS ETHICS MODULE 1 UNIT I_A.pdfDr Vijay Vishwakarma
106 views25 slides
BUSINESS ETHICS MODULE 1 UNIT I_B.pdf by
BUSINESS ETHICS MODULE 1 UNIT I_B.pdfBUSINESS ETHICS MODULE 1 UNIT I_B.pdf
BUSINESS ETHICS MODULE 1 UNIT I_B.pdfDr Vijay Vishwakarma
63 views21 slides
Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating... by
Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...
Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...Taste
39 views34 slides
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab... by
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...RAHUL PAL
53 views26 slides
JRN 362 - Lecture Twenty-Two by
JRN 362 - Lecture Twenty-TwoJRN 362 - Lecture Twenty-Two
JRN 362 - Lecture Twenty-TwoRich Hanley
41 views157 slides

Recently uploaded(20)

Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating... by Taste
Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...
Creative Restart 2023: Christophe Wechsler - From the Inside Out: Cultivating...
Taste39 views
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab... by RAHUL PAL
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
RAHUL PAL53 views
JRN 362 - Lecture Twenty-Two by Rich Hanley
JRN 362 - Lecture Twenty-TwoJRN 362 - Lecture Twenty-Two
JRN 362 - Lecture Twenty-Two
Rich Hanley41 views
The Future of Micro-credentials: Is Small Really Beautiful? by Mark Brown
The Future of Micro-credentials:  Is Small Really Beautiful?The Future of Micro-credentials:  Is Small Really Beautiful?
The Future of Micro-credentials: Is Small Really Beautiful?
Mark Brown131 views
Artificial Intelligence and The Sustainable Development Goals (SDGs) Adoption... by BC Chew
Artificial Intelligence and The Sustainable Development Goals (SDGs) Adoption...Artificial Intelligence and The Sustainable Development Goals (SDGs) Adoption...
Artificial Intelligence and The Sustainable Development Goals (SDGs) Adoption...
BC Chew55 views
Introduction to AERO Supply Chain - #BEAERO Trainning program by Guennoun Wajih
Introduction to AERO Supply Chain  - #BEAERO Trainning programIntroduction to AERO Supply Chain  - #BEAERO Trainning program
Introduction to AERO Supply Chain - #BEAERO Trainning program
Guennoun Wajih142 views
UNIT NO 13 ORGANISMS AND POPULATION.pptx by Madhuri Bhande
UNIT NO 13 ORGANISMS AND POPULATION.pptxUNIT NO 13 ORGANISMS AND POPULATION.pptx
UNIT NO 13 ORGANISMS AND POPULATION.pptx
Madhuri Bhande59 views
What is Digital Transformation? by Mark Brown
What is Digital Transformation?What is Digital Transformation?
What is Digital Transformation?
Mark Brown56 views
Interaction of microorganisms with Insects.pptx by MicrobiologyMicro
Interaction of microorganisms with Insects.pptxInteraction of microorganisms with Insects.pptx
Interaction of microorganisms with Insects.pptx
Guess Papers ADC 1, Karachi University by Khalid Aziz
Guess Papers ADC 1, Karachi UniversityGuess Papers ADC 1, Karachi University
Guess Papers ADC 1, Karachi University
Khalid Aziz119 views
Career Building in AI - Technologies, Trends and Opportunities by WebStackAcademy
Career Building in AI - Technologies, Trends and OpportunitiesCareer Building in AI - Technologies, Trends and Opportunities
Career Building in AI - Technologies, Trends and Opportunities
WebStackAcademy56 views

Recent Advances in Computer Vision

  • 1. Recent Advances in Computer Vision Ming-Hsuan Yang
  • 2. Computer vision • Holly grail – tell a story from an image
  • 3. History • “In the 1960s, almost no one realized that machine vision was difficult.” – David Marr, 1982 • Marvin Minsky asked Gerald Jay Sussman to “spend the summer linking a camera to a computer and getting the computer to describe what it saw” – Crevier, 1993 • 40+ years later, we are still working on this
  • 6. 1990s • Face detection • Particle filter • Pfinder • Normalized cut
  • 7. 2000s • SIFT – Mosaicing, panorama – Object recognition – Photo tourism, photosynth – Human detection • Adaboost-based face detector
  • 9. Conferences • CVPR – Computer Vision and Pattern Recognition, since 1983 – Annual, held in US • ICCV – International Conference on Computer Vision, since 1987 – Every other year, alternate in 3 continents • ECCV – European Conference on Computer Vision, since 1990 – Every other year, held in Europe
  • 10. Conferences (cont’d) • ACCV – Asian Conference on Computer Vision • BMVC – British Machine Vision Conference • ICPR – International Conference on Pattern Recognition • SIGGRAPH • NIPS – Neural Information Processing Systems
  • 11. Conferences (cont’d) • MICCAI – Medical Image Computing and Computer-Assisted Intervention • ISBI – International Symposium on Biomedical Imaging • FG – IEEE Conference on Automatic Face and Gesture Recognition • ICCP, ICDR, ICVS, DAGM, CAIP, MVA, AAAI, IJCAI, ICML, ICRA, ICASSP, ICIP, SPIE, DCC, WACV, 3DPVT, ACM Multimedia, ICME, …
  • 12. Conference organization • General chairs: administration • Program chairs: handling papers • Area chairs: – Assign reviewers – Read reviews and rebuttals – Consolidation reports – Recommendation • Reviewers • Authors
  • 13. Review process • Submission • CVPR/ECCV/ICCV – Double blind review – Program chairs: assign papers to area chairs – Area chairs: assign papers to reviewers • Rebuttal
  • 14. Area chair meetings • 2 day meetings • Several panels • Each paper is reviewed by at least 2 area chairs • Buddy system • Area chair make recommendations • Program chairs make final decisions
  • 15. Conference acceptance rates • ICCV/CVPR/ECCV: ~ 30% • ACCV (2009): ~ 30% • NIPS: ~ 30% • BMVC: ~ 40% • ICIP: ~ 45% • ICPR: ~ 55% • Disclaimer – low acceptance rate = high quality?
  • 16. CVPR Submission Oral Overall
  • 17. ICCV Submission Oral Overall
  • 18. ECCV Submission Oral Overall
  • 19. Journals • PAMI – IEEE Transactions on Pattern Analysis and Machine Intelligence, since 1979 (impact factor: 5.96, #1 in all engineering and AI, top-ranked IEEE and CS journal) • IJCV – International Journal on Computer Vision, since 1988 (impact factor: 5.36, #2 in all engineering and AI) • CVIU – Computer Vision and Image Understanding, since 1972 (impact factor: 2.20)
  • 20. Journals (cont’d) • IVC – Image and Vision Computing • IEEE Transactions on Medical Imaging • TIP – IEEE Transactions on Image Processing • MVA – Machine Vision and Applications • PR – Pattern Recognition • TM – IEEE Transactions on Multimedia • …
  • 21. PAMI review process • Editor-in-chief (EIC) assigns papers to associate editors (AE) • AE assigns reviewers • First-round review: 3-6 months – Accept as is – Accept with minor revision – Major revision – Resubmit as new – Reject
  • 22. PAMI review process (cont’d) • Second-round review: 2-4 months – Accept as is – Accept with minor revision – Reject • EIC makes final decision • Overall turn-around time: 6 to 12 months • Rule of thumb: 30% additional work beyond a CVPR/ICCV/ECCV paper
  • 23. IJCV/CVIU review process • Similar formats • CVIU has roughly the same turn-around time as PAMI • IJCV tends to have longer turn-around time
  • 24. Journal acceptance rate • PAMI, IJCV: ~ 30% • CVIU: ~ 30%
  • 25. Tools • Google scholar, citeseer, • h-index • Software: publish or perish • Disclaimer: – h index = significance? – # of citation = significance
  • 26. How to get your papers rejected? • Refer to Jim Kajia (SIGGRAPH 93 papers chair): How to get your SIGGRAPH paper rejected? • Do not – Pay attention to review process – Put yourself as a reviewer perspective – Put the work in right context – Carry out sufficient amount of experiments – Compare with state-of-the-art algorithms – Pay attention to writing
  • 27. Pay attention to review process • Learn how others/you can pick apart a paper • Learn from other’s mistakes • Learn how to write good papers • Learn what it takes to get a paper published
  • 28. Put yourself as reviewer • What are the contributions? • Does it advance the science in the filed? • Why you should accept this paper? • Is this paper a case study? • Is this paper interesting? • What is the audience? • Does anyone care about this work?
  • 29. Experimental validation • Common data set • Killer data set • Large scale experiment • Evaluation metric
  • 30. Compare with state of the art • Do your homework • Need to know what is out there • Need to show why one’s method outperforms others, and in what way? – speed? – accuracy? – easy to implement? – general application?
  • 31. Writing • Clear presentation • Terse • Careful about wording • Make claims with strong evidence
  • 32. Review form • Summary • Overall Rating – Definite accept, weakly accept, borderline, weakly reject, definite reject • Novelty – Very original, original, minor originality, has been done before • Importance/relevance – Of broad interest, interesting to a subarea, interesting only to a small number of attendees, out of CVPR scope
  • 33. Review form (cont’d) • Clarity of presentation – Reads very well, is clear enough, difficult to read, unreadable • Technical correctness – Definite correct, probably correct but did not check completely, contains rectifiable errors, has major problems • Experimental validation – Excellent validation or N/A (a theoretical paper), limited but convincing, lacking in some aspects, insufficient validation • Additional comments • Reviewer’s name
  • 34. Challenging issues • Large scale • Unconstrained • Real-time • Robustness • Recover from failure – graceful dead
  • 35. Some hot topics • Object recognition, categorization • Internet scale image search • Video search • Human detection • 3D human pose estimation • Computational photography • Scene understanding
  • 36. Some hot tools • Prior • Context • Sparse representation • Multiple instance learning • Online learning • Convex optimization • Constraint • Hashing
  • 37. Prior Torralba and Sinha ICCV 01
  • 38. Prior Heitz and Koller ECCV 08
  • 39. Prior Jia CVPR 08 He et al. CVPR 09
  • 40. Scene understanding Leibe et al. CVPR 07
  • 41. Image search Wu et al. CVPR 09
  • 42. Computational photography Johnson and Adelson et al. CVPR 09