Advanced Computer Vision Final Projects

Highlighted project:
Avery Allen and Wenchen Li, Generative Adversarial Denoising Autoencoder for Face Completion. [webpage]

All projects:
Cusuh Ham, Sketch-Based Image Synthesis. [webpage]
John Turner and Siddharth Raja, O'FaMACap dataset (Obama Face&Mouth Image/Audio/Caption) and LSTM-based lipreader. [webpage]
Carl Saldanha, Visual Question Generation. [webpage]
Varun Agrawal and Palash Shastri, Deep Learning on the Yelp Image Dataset. [webpage]
Vasavi Gajarla and Aditi Gupta, Emotion Detection and Sentiment Analysis of Images. [pdf]
Avinash Bhaskaran and Anusha Sridhar Rao, Structure from Motion using Uncalibrated Cameras. [pdf]
Huda Alamri and Julia Deeb, Diving Deeper into IM2GPS. [pdf]
Jonathan Suit, Generating Facial Expressions. [pdf]
Punarva Katte and Prabhudev Prakash, Billboard Content Recognition for Driver Assistance Systems. [pdf]
Sam Seifert, Autocomplete Sketch Tool. [pdf]
Shantanu Deshpande and Naman Goyal, Sketch Based Image Retrieval. [pdf]
Stefano Fenu and Carden Bagwell, Image Colorization using Residual Networks. [pdf]

Final projects

Hi class, I intend to post the final projects on the class webpage and blog. If you don't want your project posted then let me know.

Talks of Interest - Devi Parikh and Dhruv Batra

We have two visitors whose work has come up in this class. Devi Parikh will give a talk in TSRB in the second floor GVU cafe at 11:00 today (Tuesday). Dhruv Batra will give a talk at the same location on Wednesday. Topics include the Visual Question Answering task that we've addressed in class. Please attend if you can.

Final Presentations - Friday, April 29, 8am

We will have final project presentations this Friday during the final exam slot. Please aim for the same 6 minute presentation length that has been recommended all semester.

As the course syllabus says "Students will also produce a conference-formatted write-up of their project. Projects will be published on the this web page". This will not be due on Friday, but instead Wednesday, May 4th. Also, you have the option of producing either a conference-formatted pdf (download something like the CVPR author toolkit) or a web page with a similar level of detail. The level of detail should be that of a "short paper", i.e. about 4 pages with figures and references. It's OK if the writeup is longer.

Fri, April 22 - Sketchy Database

The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies. Patsorn Sangkloy, Nathan Burnell, Cusuh Ham, James Hays. Siggraph 2016

This is our last paper. The camera ready is tomorrow so the paper will be posted on Thursday.

Edit: Here is the paper. Since I'm making this available so late don't worry about the summaries or questions. Feel free to post if you do have comments, though.

Wed, April 20 - LSDA

LSDA: Large Scale Detection Through Adaptation. Judy Hoffman, Sergio Guadarrama, Eric Tzeng, Ronghang Hu, Jeff Donahue, Ross Girshick, Trevor Darrell, Kate Saenko. 2014.
arXiv

Varun will spend some time discussion this paper first:
Rich feature hierarchies for accurate object detection and semantic segmentation. Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. 2014.
arXiv

Mon, April 18 - Adverserial Networks

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Alec Radford, Luke Metz, Soumith Chintala. 2015.

project page, arXiv