CS 216/295: Image Understanding

Fall 2008

Project Ideas

Interesting Recent Papers

Research papers from ECCV 2008
Research papers from CVPR 2008

Auto-context and Its Application to High-level Vision Tasks, Zhuowen Tu, CVPR, 2008

Particle Video: Long-Range Motion Estimation Using Point Trajectories, Peter Sand and Seth Teller, CVPR'06.

Putting Objects in Perspective, Derek Hoiem, Alexei Efros, and Martial Hebert, CVPR'06.

Using Multiple Segmentations to Discover Objects and their Extent in Image Collections, Bryan Russell, Alexei Efros, Josef Sivic, William Freeman, and Andrew Zisserman, , CVPR'06.

Aligning Sequences and Actions by Maximizing Space-Time Correlations, ECCV'06, Ukrainitz and Irani,

Learning to Combine Bottom-Up and Top-Down Segmentation, Levin and Weiss, ECCV'06.

Extracting Subimages of an Unknown Category from a Set of Images, CVPR'06 Sinisa Todorovic and Narendra Ahuja.

Multiple Object Class Detection with a Generative Model, Krystian Mikolajczyk,Bastian Leibe,Bernt Schiele

Image Completion Using Global Optimization Nikos Komodakis and Georgios Tziritas, CVPR 2006.

The Design of High-Level Features for Photo Quality Assessment, Yan Ke, Xiaoou Tang, Feng Jing, CVPR 2006.

Example Based 3D Reconstruction from Single 2D Images, Tal Hassner and Ronen Basri, CVPR 2006.

Multiclass Object Recognition with Sparse, Localized Features, J. Mutch and D. Lowe, CVPR 2006.

Discovering Objects and their Location in Images, Josef Sivic, Bryan Russell, Alexei A. Efros, Andrew Zisserman, Bill Freeman, ICCV 2005.

GrabCut: Interactive Foreground Extraction using Iterated Graph Cuts. C. Rother, V. Kolmogorov, A. Blake. ACM Transactions on Graphics (SIGGRAPH'04), 2004

Geometric context from a single image, Hoiem, Efros, Hebert, ICCV 2005.

Learning Hierarchical Models of Scenes, Objects, and Parts, Suddert, Torralba, Freeman, Willsky, ICCV 2005

Describing Visual Scenes using Transformed Dirichlet Processes Sudderth, Torralba, Freeman, Willsky, NIPS 2005

The Pyrmaid Match Kernel: Discriminative Classification with sets of image Features Grauman, Darrell, ICCV 2005

Scale and Affine Invariant Interest Point Detectors Mikolajczyk, Schmid, IJCV 2004

Features for Recognition: Viewpoint Invariance of non-planar scenes Vedaldi, Soatto, ICCV 2005

Pictoral Structures for Object Recognition Felzenszwalb, Huttenlocher, IJCV 2005

A Discriminatively Trained, Multiscale, Deformable Part Model Felzenszwalb, McAllester, Ramanan, CVPR 2008

Interesting Datasets

LabelMe a large database of over 10,000 annotated images with over 2,000 different object descriptions.

The PASCAL Object Recognition Database Collection

Caltech 101 and 256 labeled pictures of objects belonging to 101/256 object categories.

CMU face databases

MIT databases for faces, pedestrians and cars

GRAZ 02 database of segmentation masks for bikes people and cars

UIUC Image Database for Car Detection

ETH-80 database for object categorization

Wordnet A searchable database of the relationships between different words. Useful for automatically determining what image annotations mean.

Flickr has a large collection of searchable images which can be automatically downloaded (ask for details) Aerial images of the entire California coastline are available here.

The Computer Vision Homepage contains an extensive list of other databases

Other Ideas

A list of fun project ideas from Serge Belongie at UCSD here