CAP 6412 - Advanced Computer Vision

Spring 2014
TuTh 3:00PM - 4:15PM
ENG1 383


Instructor: Imran Saleemi
Email: imran at eecs dot ucf dot edu
Office: HEC 256
Office hours: TuTh 2:00PM - 3:00PM

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 25%
Paper Presentations 10%
Discussion and Attendance 20%
Programming Projects 45%
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 7 & 9
Lecture 3 - Jan 14

L. Zhang, and L. van der Maaten, "Structure Preserving Object Tracking", CVPR 2013.

Presenter: Afshin Dehghan

Lecture 4 - Jan 16

Florent Perronnin, and Christopher Dance, "Fisher Kernels on Visual Vocabularies for Image Categorization", CVPR 2007.

Presenter: Gonzalo Vaca [slides]

Lecture 5 - Jan 21

Fisher Kernels (cont'd)

Florent Perronnin, and Christopher Dance, "Fisher Kernels on Visual Vocabularies for Image Categorization", CVPR 2007.

Presenter: Gonzalo Vaca

Lecture 6 - Jan 23

M. Chen, A. Zheng, and K. Weinberger, "Fast Image Tagging", ICML 2013.

Presenter: Mahdi Kalayeh

Lecture 7 - Jan 28

D. Oneata, J. Verbeek, and C. Schmid, "Action and Event Recognition with Fisher Vectors on a Compact Feature Set", ICCV 2013.

Presenter: Bo Yang

Lecture 8 - Jan 30

Siyu Tang, Mykhaylo Andriluka, Anton Milan, Konrad Schindler, Stefan Roth, and Bernt Schiele, "Learning People Detectors for Tracking in Crowded Scenes", ICCV 2013.

Presenter: Vinay Hegde

Lecture 9 - Feb 4

Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, and Antonio Torralba, "HOGgles: Visualizing Object Detection Features", ICCV 2013.

Presenter: Sarfaraz Hussein

Lecture 10 - Feb 6

Vignesh Ramanathan, Percy Liang, and Li Fei-Fei, "Video Event Understanding using Natural Language Descriptions", ICCV 2013.

Presenter: Somayeh Keshavarz

Lecture 11 - Feb 11

Ofir Pele, and Michael Werman, "Fast and Robust Earth Mover’s Distances", ICCV 2009.

Presenter: Yang Zhang

Lecture 12 - Feb 13

Asad Butt, and Robert Collins, "Multi-target Tracking by Lagrangian Relaxation to Min-Cost Network Flow", ICCV 2013.

Presenter: Aidean Sharghi

Lecture 13 - Feb 18

Anestis Papazoglou, and Vitto Ferrari, "Fast object segmentation in unconstrained video", ICCV 2013.

Presenter: Amir Mazaheri

Lecture 14 - Feb 20

A Tutorial on Deep Learning

by Dr. Rahul Sukthankar

Lecture 15 - Feb 25

Xiaofeng Ren, and Liefeng Bo, "Discriminatively Trained Sparse Code Gradients for Contour Detection", NIPS 2012.

Presenter: Dong Zhang

Lecture 16 - Feb 27

Matthew Zeiler, and Rob Fergus, "Visualizing and Understanding Convolutional Networks", arXiv 1311.2901, Nov 2013.

Presenter: Oliver Nina

Lecture 17 - Mar 11

Bogdan Alexe, Nicolas Heess, Yee Whye Teh, and Vittorio Ferrari, "Searching for objects driven by context", NIPS 2012.

Presenter: Khurram Soomro

Lecture 18 - Mar 13

Caglayan Dicle, Mario Sznaier, and Octavia Camps, "The Way They Move: Tracking Multiple Targets with Similar Appearance", ICCV 2013.

Presenter: Haroon Idrees

Lecture 19 - Mar 18

No paper discussion/report

Programming assignment I discussion and feedback

Lecture 20 - Mar 20

Anelia Angelova, and Shenghuo Zhu, "Efficient object detection and segmentation for fine-grained recognition", CVPR 2013.

Presenter: Guang Shu

Lecture 21 - Mar 25

Weihong Deng, Jiani Hu, and Jun Guo, "In Defense of Sparsity Based Face Recognition", CVPR 2013.

Presenter: Enrique Ortiz

Lecture 22 - Mar 27

Bowen Jiang, Lihe Zhang, Huchuan Lu, Chuan Yang, and Ming-Hsuan Yang, "Saliency Detection via Absorbing Markov Chain", ICCV 2013.

Presenter: Nasim Souly

Lecture 23 - Apr 1   [Programming Assgn II due]

Seunghoon Hong, Suha Kwak, Bohyung Han, "Orderless Tracking through Model-Averaged Posterior Estimation", ICCV 2013.

Presenter: Liuliu Wu

Lecture 24 - Apr 3

Zhenhua Wang, Qinfeng Shi, Chunhua Shen and Anton van den Hengel, "Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs", CVPR 2013.

Presenter: Salman Khokhar

Lecture 25 - Apr 8

Programming assignment III -- [Due Apr 29 -- 12pm]

Lecture 26 - Apr 15

Marcus Rohrbach, Michaela Regneri, Mykhaylo Andriluka, Sikandar Amin, Manfred Pinka, and Bernt Schiele, "Script Data for Attribute-based Recognition of Composite Activities", ECCV 2012.

Presenter: Sarfaraz Hussein


Mihai Surdeanu, Julie Tibshirani, Ramesh Nallapati, and Christopher D. Manning, "Multi-instance Multi-label Learning for Relation Extraction", EMNLP-CoNLL 2012.

Presenter: Somayeh Keshavarz

Lecture 27 - Apr 17

Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, and Philip Torr, "BING: Binarized Normed Gradients for Objectness Estimation at 300fps", CVPR 2014.

Presenter: Yang Zhang


Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, and Li Fei-Fei, "Large-scale Video Classification with Convolutional Neural Networks", CVPR 2014.

Presenter: Oliver Nina

List of Papers to choose from:

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

Motion and Tracking:
Hongyi Zhang, Andreas Geiger, and Raquel Urtasun, "Understanding High-Level Semantics by Modeling Traffic Patterns", ICCV 2013.
Yu Pang, Haibin Ling, "Finding the Best from the Second Bests – Inhibiting Subjective Bias in Evaluation of Visual Tracking Algorithms", ICCV 2013.
Zhuwen Li, Jiaming Guo,, Loong-Fah Cheong, and Zhiying Zhou, "Perspective Motion Segmentation via Collaborative Clustering", ICCV 2013.
Saad Ali, "Measuring Flow Complexity in Videos", ICCV 2013.
Seunghoon Hong, Suha Kwak, Bohyung Han, "Orderless Tracking through Model-Averaged Posterior Estimation", ICCV 2013.
Caglayan Dicle, Mario Sznaier, Octavia Camps, "The Way They Move: Tracking Multiple Targets with Similar Appearance", ICCV 2013.
Siyu Tang, Mykhaylo Andriluka, Anton Milan, Konrad Schindler, Stefan Roth, Bernt Schiele, "Learning People Detectors for Tracking in Crowded Scenes", ICCV 2013.

Visual Saliency:
Nicolas Riche, Matthieu Duvinage, Matei Mancas, Bernard Gosselin, Thierry Dutoit, "Saliency and Human Fixations: State-of-the-art and Study of Comparison Metrics", ICCV 2013.
Bowen Jiang, Lihe Zhang, Huchuan Lu, Ming-Hsuan Yang, Chuan Yang, "Saliency Detection via Absorbing Markov Chain", ICCV 2013.
Yangqing Jia, Mei Han, "Category-Independent Object-level Saliency Detection", ICCV 2013.
Xiaohui Li, Huchuan Lu, Ming-Hsuan Yang, Lihe Zhang, Xiang Ruan, "Saliency Detection via Dense and Sparse Reconstruction", ICCV 2013.
Hyun Soo Park, Eakta Jain, Yaser Sheikh, "Predicting Primary Gaze Behavior using Social Saliency Fields", ICCV 2013.
Elizabeth Shtrom, George Leifman, Ayellet Tal, "Saliency Detection in Large Point Sets", ICCV 2013.

Detection/Categorization
Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba, "HOGgles: Visualizing Object Detection Features", ICCV 2013.
Iasonas Kokkinos, "Shufflets: shiftable shared parts for multi-category detection", ICCV 2013.

Segmentation, Grouping:
Anestis Papazoglou, Vitto Ferrari, "Fast object segmentation in unconstrained video", ICCV 2013.

Scene classification/segmentation, Image Retrieval:

Action, Activity, Event Recognition:
Mohamed Amer, Sinisa Todorovic, Alan Fern, and Song Chun Zhu, "Monte Carlo Tree Search for Scheduling Activity Recognition", ICCV 2013.
LiMin Wang, and Yu Qiao, "Mining Motion Atoms and Phrases for Complex Action Recognition", ICCV 2013.
Hueihan Jhuang, Juergen Gall, Michael Black, and Cordelia Schmid, "Towards understanding action recognition", ICCV 2013.