Bay Area Vision Meeting (BAVM 2009)

Image and Video Understanding

August 14th, 2009. 12:30-6:30pm.
Stanford University

Did you miss BAVM 2009?

Details about BAVM 2010 are now available!


The Bay Area Vision Meeting (BAVM) is an informal gathering (without a printed proceedings) of academic and industry researchers with interest in computer vision and related areas. The goal is to build community among vision researchers in the San Francisco Bay Area, however, visitors and travelers from afar are also encouraged to attend and present. New research, previews of work to be shown at upcoming vision conferences, reviews of not-well-publicized work, and descriptions of "work in progress" are all welcome.

Topic and Format

The topic of BAVM 2009 is Image and Video Understanding. This half-day meeting will consist of keynote speeches by invited speakers as well as demos and poster sessions. We will host posters and demos, and a few selected demos will be highlighted on a Demo Spotlight. The meeting is open to all researchers, faculty and students.


A downloadable program is available here.

Confirmed Speakers


  • 12:30-1:15pm Registration
  • 12:30-1:15pm Social gathering and informal presentations
  • 1:15-1:20pm Welcome message
  • 1:20-1:40pm Invited talk: Jitendra Malik
  • 1:40-2:00pm Invited talk: Jack Gallant
  • 2:00-2:20pm Invited talk: Li Fei-Fei
  • 2:20-3:20pm Poster Session 1
  • 3:20-3:40pm Invited talk: Trevor Darrell
  • 3:40-4:00pm Invited talk: Jay Yagnik
  • 4:00-4:30pm Demo spotlight
  • 4:30-6:00pm Poster Session 2 & Demos

Poster Session 1

  1. Image-based Retrieval with a Camera Phone. Sam S. Tsai.
  2. Training-free Nonparametric Object and Action Detection from Images and Video. Hae Jong Seo.
  3. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. Honglak Lee.
  4. Kernelized Locality-Sensitive Hashing for Scalable Image Search. Brian Kulis.
  5. Measurement of eye velocity using active illumination. Jeff Mulligan.
  6. Max Margin Additive Classifiers for Detection. Subhransu Maji.
  7. Streaming Mobile Augmented Reality. David M. Chen.
  8. Categorization of good and bad examples of natural scene categories. Barry Chai.
  9. Transient Rendering. Adam Smith.
  10. Recognition Using Regions. Chunhui Gu.
  11. Reading Challenging Barcodes with Cameras. Orazio Gallo.
  12. Multimodal retrieval for diagnostic decision support. Tanveer Syeda-Mahmood.
  13. Making The Real World Virtual: Tracking Board Game Pieces. Steven Scher.
  14. A Region-based Approach to Scene Understanding. Stephen Gould.
  15. Extracting Moving People from Internet Videos. Juan Carlos Niebles, Bohyung Han, Andras Ferencz, Li Fei-Fei.
  16. Segmentation of Brain Tumors based on Multi-Modality Magnetic Resonance Images and Spectroscopy. Alexandra Constantin, Ruzena Bajcsy, Sarah Nelson.
  17. From Contours to Regions: An Empirical Evaluation. Michael Maire.

Demo Spotlight

  1. Mediating Reality (Realtime Autostereo Capture/Display). Harlyn Baker, Zeyu Li. HP Labs/UC Berkeley.
  2. Visual Product Search. Mark Ruzon.
  3. Realtime 3D Vision. John Woodfill. TYZX, Inc.
  4. Large Scale Content-Based Web Image Search. Qifa Ke. Microsoft Research Silicon Valley.
  5. Image similarity at Navneet Dalal.

Poster Session 2

  1. Color constancy of 3D objects: effect of surface material properties. Bei Xiao.
  2. Distributed multiview image coding through unsupervised learning of disparity. David Varodayan.
  3. Unsupervised Learning of Stereo Vision with Monocular Cues. Hoang Trinh.
  4. Large Displacement Optical Flow. Thomas Brox.
  5. Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition. Bangpeng Yao.
  6. A Novel Feature Descriptor Invariant to Complex Brightness Changes. Feng Tang, Suk-Hwan Lim, Nelson L. Chang.
  7. Beyond Categories: Recognition by Association via Learning Per-exemplar Distances. Tomasz Malisiewicz.
  8. A Multi-View Probabilistic Model for 3D Object Classes. Hao Su, Min Sun.
  9. Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations. Lubomir Bourdev.
  10. Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction. Damian Eads.
  11. Probabilistic Matching of Lines for Their Homography. Taemin Kim.
  12. Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework. Li-Jia Li.
  13. ImageNet: A Large-Scale Hierarchical Image Database. Jia Deng.
  14. MAP Estimation of Semi-Metric MRFs via Hierarchical Graph Cuts. Pawan Mudigonda.
  15. Context by Region Ancestry. Joseph Lim.
  16. Automatic Segmentation and Structural Study of the Bacterial Cell Wall. Fernando Amat, Farshid Moussavi.
  17. Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories. Hao Su, Min Sun.
  18. Bayesian Localized Multiple Kernel Learning. Mario Christoudias, Raquel Urtasun and Trevor Darrell.

Guidelines for Presenters

Posters: Each poster has been assigned to a specific board. Authors can find their tack board location via labels with a poster ID number. The poster ID number can be found in the meeting program above. Note that each poster will be displayed throughout the entire meeting. Presenters can put up their posters any time prior to their session. Please note that the MAXIMUM POSTER SIZE that will fit into the boards is 4ft by 4ft.

Demos: The demo presentation will consist of a 5 minute talk during the demo spotlight plus a 1.5 hour window where you will be able to make a live demonstration of your technology.


Confirmed Attendees


  • Mridul Aanjaneya
  • Fernando Amat
  • Rahul Biswas
  • Barry Chai
  • David M. Chen
  • Louis Chen
  • Man Cheung
  • Adam Coates
  • Jingyu Cui
  • Jia Deng
  • Jennifer Dolson
  • Li Fei-Fei
  • Shangping Feng
  • Kevin Gabayan
  • Varun Ganapathi
  • Juan (Jo Ann) Gao
  • Tianshi Gao
  • Stephen Gould
  • Kalanit Grill-Spector
  • Leonidas Guibas
  • Pat Hanrahan
  • Kyle Heath
  • Jeffrey Heer
  • David Jackson
  • Xiaoye Jiang
  • Amir hossein Khalili
  • Farnaz Ronaghi Khameneh
  • Tamaki Kojima
  • Daphne Koller
  • Steven Lansel
  • Quoc V. Le
  • Honglak Lee
  • Li-Jia Li
  • Takao Morita
  • Farshid Moussavi
  • Pawan Mudigonda
  • Vidhya Navalpakkam
  • Andrew Ng
  • Juan Carlos Niebles
  • Adam November
  • Manu Parmar
  • Christian Plagemann
  • David Remus
  • Olga Russakovsky
  • Richard Socher
  • Kahye Song
  • David Stavens
  • Michael Styer
  • Hao Su
  • Gabriel Takacs
  • Alex Teichman
  • Sebastian Thrun
  • Ju Tian
  • Sam Tsai
  • Adam Vogel
  • Brian Wandell
  • Fan Wang
  • Zixuan Wang
  • Chen Wu
  • Jiajing Xu
  • Bangpeng Yao
  • Yuan Yao

UC Berkeley

  • Maneesh Agrawala
  • Pablo Arbelaez
  • Ruzena Bajcsy
  • Jonathan Barron
  • Lubomir Bourdev
  • Thomas Brox
  • Charles Cadieu
  • Meng Cao
  • Dan Coates
  • Alexandra Constantin
  • C. Mario Christoudias
  • Trevor Darrell
  • Ashley Eden
  • Mario Fritz
  • Jack Gallant
  • Ricardo Garcia
  • Pierre Garrigues
  • Carl Henrik Ek
  • Paul Ivanov
  • Kilian Koepsell
  • John Kua
  • Brian Kulis
  • Thomas Lauritzen
  • Zeyu Li
  • Jitendra Malik
  • Michael Maire
  • Subhransu Maji
  • Nikhil Naikal
  • Ravi Ramamoorthi
  • Mathieu Salzmann
  • Lei Shi
  • An Vu
  • Chunli Vu
  • Jimmy Wang
  • Allen Yang

UC Santa Cruz

  • Bin An
  • Priyam Chatterjee
  • James Davis
  • Damian Eads
  • Orazio Gallo
  • Prabath Gunawardane
  • David Helmbold
  • Peyman Milanfar
  • Steven Scher
  • Hae Jong Seo
  • Adam Smith
  • Hiroyuki Takeda
  • Qi Zhao
  • Xiang Zhu

UC Merced

  • Daniel Leung
  • Shawn Newsam
  • Zaihong Shuai
  • Chih-Yuan Yang
  • Ming-Hsuan Yang
  • Yang Yi

UC Irvine

  • Hamed Pirsiavash
  • Pinaki Sinha


  • Teresa Ko
  • Roozbeh Mottaghi
  • Michalis Raptis

U Southern California

  • Vivek Pradeep

U Michigan Ann-Arbor

  • Silvio Savarese
  • Min Sun

U Washington

  • Dingding Liu
  • Kathleen Tuite


  • Hoang Trinh


  • Alyosha Efros
  • Tomasz Malisiewicz

Florida State U

  • Yuhua Zhu

Oregon State U

  • Sinisa Todorovic


  • Eamon Caddigan
  • Ali Farhadi
  • Alexander Sorokin

Cornell University

  • Fang Liu

Haifa University

  • Shalomi Eldar

Princeton University

  • Kai Li

U Toronto

  • Aaron Hertzmann

Northwestern University

  • Jiang Xu

Arizona State U

  • Karthikeyan Natesan Ramamurthy
  • Jayaraman J. Thiagarajan


  • James Coughlan
  • Douglas Gray
  • Volodymyr Ivanchenko
  • Ender Tekin
  • Bei Xiao


  • Christopher Hillar


  • Terry Grant
  • Taemin Kim
  • Jeff Mulligan


  • Prabhat

HP Labs

  • Harlyn Baker
  • Nelson L. Chang
  • Hui Chao
  • Bruce Culbertson
  • Yuli Gao
  • Dan Gelb
  • Ton Kalker
  • Qian Lin
  • Tom Malzbender
  • Debargha Mukherjee
  • Ramin Samadani
  • Irwin Sobel
  • Feng Tang
  • Kar-Han Tan
  • Tong Zhang
  • Wei Zhang


  • Radek Grzeszczuk
  • Kari Pulli
  • Ramakrishna Vedantham
  • Yingen Xiong


  • Maha El Choubassi
  • Scott Ettinger
  • Horst Haussecker
  • Wei Sun
  • Yi Wu


  • Samy Bengio
  • Aparna Chennapragada
  • Tom Dean
  • Dumitru Erhan
  • Andrea Frome
  • Mei Han
  • Sergey Ioffe
  • Yushi Jing
  • Vivek Kwatra
  • Thomas Leung
  • David Ross
  • Yang Song
  • Donald Tanguay
  • George Toderici
  • Jay Yagnik
  • Hector Yee


  • Arnon Amir
  • David Beymer
  • Kilian Pohl
  • Tanveer Syeda-Mahmood
  • Fei Wang


  • Arrigo Benedetti
  • Travis Perry
  • Abbas Rafii
  • Colin Tracey


  • Joseph Santucci


  • Ali Zandifar
  • Cuiping Zhang


  • Rakesh Gupta
  • Jongwoo Lim


  • Peter Hallinan


  • Daniel Russakoff

Microsoft Research

  • Michael Isard
  • Qifa Ke
  • Oliver Williams

  • Orhan Camoglu
  • Navneet Dalal
  • Burak Gokturk
  • Diem Vu
  • Tianli Yu

Obscura Digital

  • Michael Harville


  • Jonathan Brandt
  • Scott Cohen
  • Hailin Jin
  • Zhe Lin
  • Brandon Smith


  • James Fung

Lu & Nishihara Associates

  • H Keith Nishihara

Sony Electronics Inc.

  • Shengyang Dai
  • Ming-Chang Liu
  • Akira Nakamura
  • Mark Robertson
  • Su Wang
  • William Wong
  • Liangyin Yu
  • Ximin Zhang

SRI International

  • Martin Fischler

  • Arnab Dhua
  • Sunil Ramesh
  • Mark Ruzon
  • Ryan White


  • Kuang-chih Lee


  • Matt Sandler


  • Ambrish Tyagi


  • Gaile Gordon
  • John Woodfill


  • Malcolm Slaney


  • Joe Pereira

Epson R&D

  • Chunyu Gao
  • Xianwang Wang
  • Chenyu Wu
  • Jing Xiao


  • Gregory Best
  • Gwen Byard
  • Sybor Wang


  • Hayato Ikebe
  • Shin Tanimoto

Willow Garage

  • Kurt Konolige
  • Caroline Pantofaru


  • Philipp Slusallek

PixBlitz Studios

  • Pannag Sanketi


  • Sherman Ng

NEC Labs

  • Kai Yu


  • Matt Bell
  • Judy Chen
  • Frances Mello
  • Fred Ware



Our meeting will be held at the Annenberg Auditorium, which is part of the Cummings Art Building, Stanford University. The Nathan Cummings Art Building is located at the intersection of Serra Street and Lasuen Mall on the Stanford campus, southeast of The Oval, and east of the Main Quad.




We are encouraging the attendees to register and present their POSTERS and DEMOS during the meeting. Please remember that your POSTER or DEMO from recent, previous or upcoming conferences, as well as descriptions of work in progress are all welcome to register.

Questions/Comments? Please contact Juan Carlos Niebles at jniebles at princeton edu


  • Q: How do I register?
    A: Registration is easy, you only need to fill in and submit the attendance registration form.
  • Q: I already submitted the registration form, what do I do now?
    A: You will receive a confirmation email and your name will be added to the list within 24 hours.
  • Q: Registration is closed, can I still come?
    A: Yes! We will have registration on site during the opening of the meeting.
  • Q: Will lunch be provided during registration and the social gathering time?
    A: No lunch, unfortunately. But there are several options if you need to have lunch on campus.