Final Discussion and Presentations on 11/26

There is no reading for this class.  Instead, we'll have a discussion on future directions in vision research.  Before coming to this class, you should decide what you think is the most important vision problem to work on.  That is, imagine you are a professor deciding on a project for a graduate student.  What should this project focus on?

Finally, don't forget that the final project presentations are from 5-8pm in the same room where our class normally is--NSH 3002.

Reading for 11/21

You are required to read the following paper, but not summarize it or comment on the blog.

R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation . Tech Report, 2013.

And optionally:

Abhinav Gupta and Larry S. Davis, Beyond Nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers, In ECCV 2008

Berg et. al. Understanding and Predicting Importance in Images. CVPR 2012

Krishnamuruthy and Kollar. Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World. Transactions on ACL.

Reading for 11/19

Krizhevsky, A., Sutskever, I. and Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. NIPS 2012

And optinoally:

Q.V. Le, M.A. Ranzato, R. Monga, M. Devin, K. Chen, G.S. Corrado, J. Dean, A.Y. Ng.  Building high-level features using large scale unsupervised learning..  ICML, 2012.

We will also cover the following paper, but we cannot yet post links for download (ask us if you would like a copy):

C. Szegedy, A. Toshev, D. Erhan Deep Neural Networks for Object Detection, NIPS 2013 (in press)

Reading for 11/14

S. Vijayanarasimhan and K. Grauman.  Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds. CVPR 2011.

And optionally:

J. Donahue and K. Grauman. Annotator Rationales for Visual Recognition.  ICCV 2011

B. Siddiquie and A, Gupta, Beyond Active Noun Tagging: Modeling Contextual Interactions for Multi-Class Active Learning, In CVPR 2010.

reading for 11/12

R. Fergus, Y. Weiss, and A. Torralba Semi-supervised Learning in Gigantic Image Collections. NIPS 2009

and optionally:

A. Shrivastava, S. Singh and A. Gupta. Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes. In ECCV 2012.

Guillaumin, M., Verbeek, J., Schmid, C.: Multimodal semi-supervised learning for image classification. In: CVPR. (2010)

Reading for 11/7

Y. J. Lee and K. Grauman.  Object-Graphs for Context-Aware Category Discovery. CVPR 2010

And optionally:

Bryan Russell, Alexei A. Efros, Josef Sivic, Bill Freeman, Andrew Zisserman. Using Multiple Segmentations to Discover Objects and their Extent in Image Collections. CVPR 2006

Y. J. Lee and K. Grauman.  Learning the Easy Things First: Self-Paced Visual Category Discovery. CVPR 2011

Reading for 11/5

Note: No class on 8/31

Lubomir Bourdev, Jitendra Malik, Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations, ICCV 2009

and optionally:

Saurabh Singh, Abhinav Gupta, Alexei A. Efros. Unsupervised Discovery of Mid-Level Discriminative Patches. In ECCV 2012.

Lubomir Bourdev, Subhransu Maji, Thomas Brox, Jitendra Malik, Detecting People Using Mutually Consistent Poselet Activations, ECCV 2010