- Date and Location: 12:30-6:30pm, September 14th, 2012. William R. Hewlett Teaching Center, 370 Serra Mall, Stanford University.
Demo Registration Deadline: August 26th, 2012. Poster Registration Deadline: September 3rd, 2012 (extended, limited spots, first come first serve). Attendance Registration Deadline: September 3rd, 2012 (extended).On-site registration will be available.
- Organizers: Li Fei-Fei (Stanford University). Jia Deng (Stanford University)
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 2012 is Large Scale and Fine Grained Recognition This half-day meeting will consist of keynote speeches by invited speakers as well as demos and poster sessions. The meeting is open to all researchers, faculty and students.
- Alex Berg, Stony Brook University. Toward Richer Targets in Large-Scale Recognition.
- Lubomir Bourdev, Facebook. Large-Scale Face Recognition: Analyzing Facebook Photos.
- Trevor Darrell, UC Berkeley. Concept Generalization and Pose Normalization in Fine-Grained Category Learning.
- Yuanqing Lin, NEC Labs America. Building Blocks for Fine-Grained Image Classification
- Aude Oliva, Massachusetts Institute of Technology. Massive Visual Memory.
- 11:45-12:30pm Registration and setup of poster and demos.
- 12:30-12:40pm Welcome (organizers)
- 12:40-1:20pm Invited talk: Trevor Darrell
- 1:20-2:00pm Invited talk: Yuanqing Lin
- 2:00-3:00pm Posters and demos
- 3:00-3:40pm Invited talk: Aude Oliva
- 3:40-4:20pm Invited talk: Alex Berg
- 4:20-5:00pm Invited talk: Lubomir Bourdev
- 5:00-6:30pm Additional time for posters and demos
- Large-Scale GP Classification with Flexible Adaptive Histogram Kernels. Erik Rodner.
- Scribble Tracker: A Matting-based Approach for Robust Tracking. Jialue Fan.
- Fine-Grained Categorization for 3D Scene Understanding. Michael Stark.
- Analyzing 3D Objects in Cluttered Images. Mohsen Hejrati.
- Object-centric spatial pooling for image classification. Olga Russakovsky.
- What Makes a Good Detector? -- Structured Priors for Learning From Few Examples. Tianshi Gao.
- Hedging Your Bets: Optimizing Accuracy-Specificity Trade-offs in Large Scale Visual Recognition. Jonathan Krause.
- Autonomous exploration using rapid perception of low-resolution image information. Vidya N. Murali.
- Pixel-wise Motion Detection in Persistent Aerial Video Surveillance. Grace Vesom.
- Proximate Sensing: Geographic Knowledge Discovery in Community-Contributed Photo Collections. Daniel Leung.
- Beobot 2.0: Autonomous Mobile Service Robotic Project. Christian Siagian.
- Steerable Part Models. Hamed Pirsiavash.
- PatchMatch-Based Content Completion of Stereo Image Pairs. Bryan Morse.
- General and Nested Wiberg Minimization. Dennis Strelow.
- What Are Good Parts for Hair Shape Modeling?. Feng Tang.
- Frequency-Space Decomposition and Acquisition of Light Transport. Dikpal Reddy.
- Multi-Component Models for Object Detection. Chunhui Gu.
- Non-parametric Models for Large Scale Aerial Image Registration. Carlos Correa.
- Fast and Easy 3D Reconstruction. Matt Bell. Matterport.
- Practical applications of large scale and fine grained recognition for smart photo albums and grocery shopping . Pierre Garrigues. IQ Engines.
- Realtime video summaries for monitoring. Douglas Johnston. Prism Skylabs.
- A Humanoid Robot for Table Tennis Playing. Yong Liu. Zhejiang University.
- Visual Search Technologies at A9. A9 Visual Search. A9.
- EVA: Engine for Visual Annotation. Jia Deng. Stanford University.
- Gesture recognition on your laptop. Navneet Dalal. Flutter.
Guidelines for Presenters
Posters: Posters will be displayed throughout the entire meeting. Presenters can put up their posters any time prior to the poster sessions. There will be no assignment of posters to specific boards. Presenters are free to choose any available boards. Please note that the MAXIMUM POSTER SIZE that will fit into the boards is 8ft by 4ft.
Demos: Each demo presentation will have a table (aproximately 3ft by 3ft) and an electric outlet. The demo tables will be cleared marked. There will be no assignment of demos to specific tables. Presenters are free to choose any available tables.
Our meeting will be held at the William R. Hewlett Teaching Center, 370 Serra Mall, Stanford University.
- Driving directions to Stanford University.
- Parking: Visitors may park in lots or spaces designated with a P or E sign. Parking in these spaces costs $1.50 per hour between 8:00am and 4:00pm. The following are the closest parking areas with walking distances to our venue: Parking Structure 1, Parking Structure 2, Li Ka Shing Center / Beckman lot, Lomita Drive in front of the Cantor Arts Center. You can also park at the Tresidder Union lot, take the free Marguerite shuttle (line Y) and get off at the Li Ka Shing Center. At these locations there are parking permit machines that accept credict card (Visa/MasterCard) or cash. For more locations please use the visitor map.
- Public Transportation from San Francisco or San Jose: Take the Caltrain to the Palo Alto Transit Center. From there, take the free Marguerite shuttle (line X) and get off at the Li Ka Shing Center.
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.
Demo registration form. Deadline: August 26th, 2012. Poster registration form. Deadline : September 3rd, 2012 (extended, limited spots, first come first serve). Attendance registration form. Deadline: September 3rd, 2012 (extended).
Questions/Comments? Please contact Jia Deng at jiadeng at cs.stanford.edu.
Q: Registration is closed, can I still come?
A: Yes! We will have registration on site during the opening of the meeting.
- 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: 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.
Q: My company has some job announcements. Can I post them somewhere at BAVM?
A: Yes. There will be two small poster boards where we post schedules. You are free to post your announcements there.
Q: I want to present my work as a poster and/or a demo at BAVM. Does it have to be in the topic of "large-scale and fine-grained recognition"?
A: No. We welcome all exciting work in computer vision! We want this to be a big party for all visioners in the Bay Area!