Sergey Karayev

Recent Research Projects

Timely Object Recognition

Our method for timely multi-class detection aims to give the best possible performance at any single point between a start time and a deadline. We formulate a dynamic, closed-loop policy that infers the contents of the image in order to decide which detector to deploy next. We evaluate our method with a novel timeliness measure, computed as the area under an Average Precision vs. Time curve.

• Timely Object Recognition
  Sergey Karayev, Tobias Baumgartner, Mario Fritz, Trevor Darrell
  NIPS 2012
  [project page] [pdf] [bibtex] [poster]

Depth-Informed Object Detection

Using the Microsoft Kinect, we gather a large dataset of indoor crowded scenes. We investigate ways to unify state-of-the-art object detection systems and improve them with depth information.

• A Category-Level 3-D Object Dataset: Putting the Kinect to Work
  Allison Janoch, Sergey Karayev, Yangqing Jia, Jonathan T. Barron, Mario Fritz, Kate Saenko, Trevor Darrell
  ICCV-W 2011
  [pdf] [bibtex] [dataset]
• Practical 3-D Object Detection Using Category and Instance-level Appearance Models
  Kate Saenko, Sergey Karayev, Yangqing Jia, Alex Shyr,
  Allison Janoch, Jonathan Long, Mario Fritz, Trevor Darrell
  IROS 2011
  [pdf] [bibtex]

Probabilistic Decomposition of Local Image Features

Our method for additively decomposing local image patches, LDA-SIFT, shows best performance on a novel transparent object recognition dataset. We recursively extend the model to multiple layers and successfully apply it to general object classification.

• A Probabilistic Model for Recursive Factorized Image Features
  Sergey Karayev, Mario Fritz, Sanja Fidler, Trevor Darrell
  CVPR 2011
  [pdf] [supplement] [bibtex] [poster] [slides]
• An Additive Latent Feature Model for Transparent Object Recognition
  Mario Fritz, Michael Black, Gary Bradski, Sergey Karayev, Trevor Darrell
  NIPS 2009
  [pdf] [bibtex]

---

Recent Non-Research Projects

Rayleigh: Multi-color Image Search

We present an open-source system for quickly searching large image collections by multiple colors given as a palette, or by color similarity to a query image.

• Rayleigh: Multi-color Image Search
  Sergey Karayev
  [project] [demo]

CabFriendly: A Cloud-based Mobile Web App

We present a mobile web app to match users who request similar trips and would like to share a cab. The application is hosted on Amazon’s EC2 service and combines several open-source frameworks (Django, PostgresQL, Redis, Node.js) with social networking and mapping APIs. The modularity of our design allows the service to easily scale in the cloud as the user base grows. The service is live.

• CabFriendly: A Cloud-based Mobile Web App
  Sergey Karayev, Adam Roberts, Harold Pimentel
  [pdf] [blog post] [use it!]