List of Lectures

List of Papers

Course Goals:

To prepare students for graduate research in computer vision.

Course Description:

Review recent advances in computer vision.

Exam and Grading Policy:

Reports 30%
Paper Presentations 10%
Discussion and Attendance 20%
Programming Projects + presentation (30+10) = 40%
No exam!

Reports:

Summary, strengths, weaknesses, ideas, questions, tools employed.

Useful Links

CAP 5415 Fall 2005
How to read a research paper (by Dr. Shah)

Lectures List

Lectures 1 & 2 - Jan 8 & 10 Introduction to the course Maximum Likelihood Estimation Expectation Maximization

Lecture 3 - Jan 15 H. Pirsiavash, D. Ramanan, C. Fowlkes, "Globally-optimal greedy algorithms for tracking a variable number of objects", CVPR 2011. Presenter: Wenhui Li

Lecture 4 - Jan 17 F. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, Shih-Fu Chang, "Weak attributes for large-scale image retrieval," CVPR 2012. Presenter: Kutalmis Akpinar

Lecture 5 - Jan 22 Zheng Wu, A. Thangali, Stan Sclaroff, M. Betke, "Coupling detection and data association for multiple object tracking", CVPR 2012. Presenter: Douglas Cooper

Lecture 6 - Jan 24 Bangpeng Yao, Xiaoye Jiang, A. Khosla, A. Lin, L. Guibas, Li Fei-fei, "Human action recognition by learning bases of action attributes and parts," ICCV 2011. Presenter: Yicong Tian

Lecture 7 - Jan 29 Ali Borji, "Boosting bottom-up and top-down visual features for saliency estimation", CVPR 2012. Presenter: Dong Zhang

Lecture 8 - Jan 31 Lingqiao Liu, Lei Wang, "What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection", CVPR 2012. Presenter: Rui Hou

Lecture 9 - Feb 5 Dong Liu, Xian-Sheng Hua, Linjun Yang, Meng Wang, Hong-Jiang Zhang, "Tag ranking", Proceedings of the 18th International Conference on World Wide Web, 2009. Presenter: Shervin Ardeshir

Lecture 10 - Feb 7 Programming assignment # 1

Lecture 11 - Feb 12 Reyes Rios Cabrera, Tinne Tuytelaars and Luc Van Gool, "Efficient Multi-Camera Detection, Tracking, and Identification using a shared set of Haar features", CVPR 2011. Presenter: Tung Khuc

Lecture 12 - Feb 14 X. Zhu, and D. Ramanan, "Face detection, pose estimation and landmark localization in the wild", CVPR 2012. Presenter: Andres Vargas

Lecture 13 - Feb 19 Jie Feng, Yichen Wei, Litian Tao, Chao Zhang, and Jian Sun, "Salient Object Detection by Composition", ICCV 2011. Presenter: Desmond Persaud

Lecture 14 - Feb 21 Lei Ding and Alper Yilmaz, "Inferring Social Relations from Visual Concepts", ICCV 2011. Presenter: Behnaz Nojavan

Lecture 15 - Feb 26 Liangliang Cao, Yadong Mu, Apostol Natsev, Shih-Fu Chang, Gang Hua, and John R. Smith, "Scene Aligned Pooling for Complex Video Recognition", ECCV 2012. Presenter: Venkatanagavalli Sidhamsetti

Lecture 16 - Feb 28 Recap of past papers; Potential ideas

Lecture 17 - Mar 12 Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, and Andrew Blake, "Real-Time Human Pose Recognition in Parts from Single Depth Images", CVPR 2011. Presenter: Oliver Nina

Lecture 18 - Mar 14 Bolei Zhou, Xiaogang Wang, and Xiaoou Tang, "Understanding Collective Crowd Behaviors: Learning a Mixture Model of Dynamic Pedestrian-Agents", CVPR 2012. Presenter: Salman Khokhar

Lecture 19 - Mar 19 Ruonan Li, and Todd Zickler, "Discriminative Virtual Views for Cross-View Action Recognition", CVPR 2012. Presenter: Soumyabrata Dey

Lecture 20 - Mar 21 Presentations: Programming Assignment I

Lecture 21 - Mar 26 Presentations: Programming Assignment I

Lecture 22 - Mar 28 Presentations: Programming Assignment I

Lecture 23 - Apr 2 Description of Programming Assignment II Due April 16 (before class)

Lecture 24 - Apr 4 Chunhui Gu, Pablo Arbeláez, Yuanqing Lin, Kai Yu, and Jitendra Malik, "Multi-Component Models for Object Detection", ECCV 2012. Presenter: Venkatanagavalli Sidhamsetti Jingen Liu, Qian Yu, Omar Javed, Saad Ali, Amir Tamrakar, Ajay Divakaran, Hui Cheng, and Harpreet Sawhney, "Video Event Recognition Using Concept Attributes", WACV 2013. Presenter: Behnaz Nojavan

List of Papers to choose from:

This will be updated through the semester. Email me to sign up.

Motion Patterns Modeling and Estimation:
Xuemei Zhao and Gerard Medioni, "Robust Unsupervised Motion Pattern Inference from Video and Applications", ICCV 2011

Visual Saliency:
Ali Borji, "Boosting bottom-up and top-down visual features for saliency estimation", CVPR 2012.

Detection/Categorization
Yuning Jiang, Jingjing Meng, Junsong Yuan, "Randomized visual phrases for object search," CVPR 2012
N. Payet, S. Todorovic, "From contours to 3D object detection and pose estimation," ICCV 2011

Scene classification/segmentation, Image Retrieval:
Liujuan Cao, Rongrong Ji, Yue Gao, Yi Yang, Qi Tian, "Weakly Supervised Sparse Coding with Geometric Consistency Pooling", CVPR 2012
Lingqiao Liu, Lei Wang, "What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection", CVPR 2012
F. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, Shih-Fu Chang, "Weak attributes for large-scale image retrieval," CVPR 2012
D. Parikh, K. Grauman, "Relative attributes", ICCV 2011

Tracking:
Zheng Wu, A. Thangali, Stan Sclaroff, M. Betke, "Coupling detection and data association for multiple object tracking", CVPR 2012
L. Leal-Taixe, G. Pons-Moll, B. Rosenhahn, "Branch-and-price global optimization for multi-view multi-target tracking," CVPR 2012
One of
H. Pirsiavash, D. Ramanan, C. Fowlkes, "Globally-optimal greedy algorithms for tracking a variable number of objects", CVPR 2011
or
J. Berclaz, F. Fleuret, E. Turetken, P. Fua, "Multiple Object Tracking Using K-Shortest Paths Optimization", PAMI 2011

Action, Activity, Event Recognition:
Lixin Duan, Dong Xu, I. Tsang, Jiebo Luo, "Visual Event Recognition in Videos by Learning from Web Data", PAMI 2012
Wen Li, Lixin Duan, Dong Xu, I. Tsang, "Text-based image retrieval using progressive multi-instance learning", ICCV 2011
Lixin Duan, Dong Xu, Shih-Fu Chang, "Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach", CVPR 2012
W. Brendel, S. Todorovic, "Learning spatiotemporal graphs of human activities," ICCV 2011
Bangpeng Yao, Xiaoye Jiang, A. Khosla, A. Lin, L. Guibas, Li Fei-fei, "Human action recognition by learning bases of action attributes and parts," ICCV 2011