Instructors:	Jason Corso (jcorso)
Course Webpage:	http://www.cse.buffalo.edu/~jcorso/t/2011F_SEM
Meeting Times:	F 1:30-4
Location:	VPML: Lockwood B20A
Office Hours:	TBA (see cal)

News

• First meeting is Friday, 9/9. Paper topics will be passed around in email beforehand.

Main Course Material

Course Overview: This is a seminar course covering advanced topics in computer vision and machine learning. We will read and discuss papers on this topic throughout the semester, with the students heavily involved in the discussions.

Prerequisites: It is assumed that the students have significance experience with computer vision, machine learning, and image analysis. Note, this is an advanced course. I have noticed many registrants in the system who are unlikely to be prepared for this course. It will likely be a waste of your time (and my time) if you have not yet sat courses like 555, 573, 574 at the bare minimum.

Grading: Grading is P/F by departmental policy.

---

Course Outline and Schedule

The list is subject to change, and it is quite longer than the number of weeks we have in the semester (we'll just continue afterwards per normal group meeting reading)... We will basically go down the list with one paper per week. Once the paper is covered, I will update this page to tell the date it was covered; prepare the next one below it for the next meeting.

• (9/9) L. Fei-Fei, A. Iyer, C. Koch, and P. Perona. What do we perceive in a glance of a real-world scene? Journal of Vision, 7(1):10, 1–29, 2007.
• (9/23) P. F. Felzenszwalb, R. B. Girhick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010.
• A. Yao, J. Gall and L. Van Gool. A Hough Transform-Based Voting Framework for Action Recognition. CVPR 2010.
• B. Eriksson, G. Dasarathy, A. Singh and R. Nowak. Active Clustering: Robust and Efficient Hierarchical Clustering Using Adaptively Selected Similarities. AISTAT 2011.
• Y. Yang and D. Ramanan. Articulated Pose Estimation with Flexible Mixtures-of-Parts. CVPR 2011.
• J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, A. Blake. Real-Time Human Pose Recognition in Parts from Single Depth Images. CVPR 2011.
• J. Liu, B. Kuipers, and S. Savarese. Recognizing Human Actions by Attributes. CVPR 2011.
• M. A. Sadeghi and A. Farhadi. Recognition Using Visual Phrases. CVPR 2011.
• H. Wang, A. Klaser, C. Schmid and C.-L. Liu. Action Recognition by Dense Trajectories. CVPR 2011.
• S. Maji, L. Bourdev, J. Malik. Action Recognition from a Distributed Representation of Pose and Appearance. CVPR 2011.
• S. Bhattacharya, R. Sukthankar, R. Jin and M. Shah. A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks. CVPR 2011.
• M. S. Ryoo and J. K. Aggarwal. Spatio-Temporal Relationship Match: Video Structure Comparison for Recognition of Complex Human Activities. ICCV 2009.
• Y. Wang, D. Tran and Z. Liao. Learning Hierarchical Poselets for Human Parsing. CVPR 2011.
• A. Kowdle, Y.-J. Chang, A. Gallagher and T. Chen. Active Learning for Piecewise Planar 3D Reconstruction. CVPR 2011.
• C.M. Carvalho, H.F. Lopes, N.G. Polson, and M. Taddy. Particle learning for general mixtures. Bayesian Analysis, 5(4):709–740, 2010.
• P.D. Hoff. Separable covariance arrays via the tucker product, with applications to multivariate relational data. Bayesian Analysis, 6(2):179–196, 2011.
• J. Mairal, F. Bach and J. Ponce. Task-driven Dictionary Learning. Technical report, HAL : inria-00521534, 2010
• A. G. Gordon and Z. Ghahramani. Generalised Wishart Processes. UAI 2011
• C. Liu and D. Sun. A Bayesian Approach to Adaptive Video Super Resolution. CVPR 2011
• H. Poon and P. Domingos. Sum-Product Networks: A New Deep Architecture. UAI 2011
• L. Li, M. Zhou, G. Sapiro, L. Carin. On the Integration of Topic Modeling and Dictionary Learning. ICML 2011. http://www.icml-2011.org/papers/375_icmlpaper.pdf
• L. Bazzani, N. Freitas, H. Larochelle, V. Murino, J. Ting. Learning attentional policies for tracking and recognition in video with deep networks. ICML 2011. http://www.icml-2011.org/papers/490_icmlpaper.pdf
• A. Coates and A. Y. Ng. The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization. ICML 2011.
• G. Kulkarni, V. Premraj, S. Dhar, S. Li, A. Berg, Y. Choi and T. Berg. Baby Talk: Understanding and Generating Image Descriptions. CVPR 2011.
• T. Jebara. Multitask Sparsity via Maximum Entropy Discrimination. JMLR 2011.
• J. A. Tropp. Two Proposals for Robust PCA Using Semidefinite Programming. Arxiv preprint arXiv:1012.1086, 2010.
• J. A. Tropp. Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions. Arxiv preprint arXiv:0909.4061, 2009.