Chenliang Xu
Fall 2017 - CSC 577: Advanced Topics in Computer Vision
Instructor: Prof. Chenliang Xu
Time/Place: MW 14:00-15:15 in 601 CSB
Office Hours: MW 13:00-14:00 in 3005 Wegmans
The syllabus is below.
Description
This course covers advanced research topics in computer vision with an emphasis on learning structured representations and embeddings. Approaches for learning from unimodal (e.g., images and videos), and multimodal data (e.g., vision and language, vision and audio) will be covered and include topics from structured predications, deep learning and others. The course will be a mix of lecture, student presentation and discussion. Prerequisites: CSC 249/449 or CSC 246/446 or CSC 298/578 (Deep Learning and Graphical Models) or permission of the instructor.
Goals
PhD Students: gain research experience in computer vision; MS Students: get prepared for a software engineer career in computer vision and artificial intelligence.
- Get exposed to a variety of topics and become familiar with state-of-the-art techniques.
- Learn to read and evaluate other peoples' work.
- Get hands dirty on a semester-long research project. (Past project has won best paper award at research conference.)
Schedule
This is a tentative schedule of the course.
Course materials will be posted on Blackboard.
Red: lecture; Blue: student presentation; Green: project presentation; Grey: no class or cancelled class.
| W | Date | Topic | Presenter |
|---|---|---|---|
| 1 | W 8/30 | Overview, Boot Camp: the Basics (read) | |
| 2 | M 9/04 | Labor Day | |
| 2 | W 9/06 | Boot Camp: CNN I (read) | |
| 3 | M 9/11 | Boot Camp: CNN II | |
| 3 | W 9/13 | Boot Camp: RNN (read) | |
| 4 | M 9/18 | Tutorial: DL Libraries and CIRC (tutorial by Lele) | Yapeng Tian, Lele Chen |
| 4 | W 9/20 | Boot Camp: Graphical Models (read, more) | |
| 5 | M 9/25 | Huang et al. CVPR 2017: Densely Connected Convolutional Network | Lele Chen |
| 5 | W 9/27 | Redmon and Farhadi, CVPR 2017: YOLO9000: Better, Faster, Stronger | Jiechen Liu |
| 6 | M 10/02 | Reed et al. NIPS 2016: Learning What and Where to Draw | Yuxiao Chen |
| 6 | W 10/04 | Luc et al. ICCV 2017: Predicting Deeper into the Future of Semantic Segmentation | Jie Chen |
| 7 | M 10/09 | Fall Break | |
| 7 | W 10/11 | Shrivastava et al. CVPR 2017: Learning from Simulated and Unsupervised Images through Adversarial Training | Jing Shi |
| 8 | M 10/16 | Xie et al. CVPR 2017: Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet | Zhe Hong |
| 8 | W 10/18 | Project Proposal | Everyone |
| 9 | M 10/23 | Villegas et al. ICML 2017: Learning to Generate Long-Term Future via Hierarchical Prediction | Hao Huang |
| 9 | W 10/25 | Aytar et al. NIPS 2016: SoundNet: Learning Sound Representations from Unlabeled Video | Ruogu Lin |
| 10 | M 10/30 | Chung et al. CVPR 2017: Lip Reading Sentences in the Wild | Wentian Zhao |
| 10 | W 11/01 | Owens et al. CVPR 2016: Visually Indicated Sounds | Zheng Zhou |
| 11 | M 11/06 | Krishna et al. ICCV 2017: Dense-Captioning Events in Videos | Zhongping Zhang |
| 11 | W 11/08 | Hendricks et al. ICCV 2017: Localizing Moments in Video with Natural Language | Gregory Hunkins |
| 12 | M 11/13 | Mattyus et al. CVPR 2016: HD Maps: Fine-grained Road Segmentation by Parsing Ground and Aerial Images | Wei Zhang |
| 12 | W 11/15 | Cancelled for CVPR | |
| 13 | M 11/20 | Castrejon et al. CVPR 2016: Learning Aligned Cross-Modal Representations from Weakly Aligned Data | Zhengyuan Yang |
| 13 | W 11/22 | Thanksgiving Recess | |
| 14 | M 11/27 | Hu et al. ICCV 2017: Learning to Reason: End-to-End Module Networks for Visual Question Answering | Yapeng Tian |
| 14 | W 11/29 | Cancelled (Prof is visiting RIT) | |
| 15 | M 12/04 | Yang et al. CVPR 2017: Deep Multimodal Representation Learning from Temporal Data | Boyuan Tian |
| 15 | W 12/06 | Kim et al. NIPS 2016: Mutlimodal Residual Learning for Visual QA | Tianlang Chen |
| 16 | M 12/11 | Project Presentation I | Group 1 |
| 16 | W 12/13 | Project Presentation II | Group 2 |
Group 1: Hao, Lele, Rougu, Tianlang, Yapeng, Yuxiao, Zheng, Zhengyuan, Zhongping
Group 2: Boyuan, Gregory, Jie, Jiechen, Jing, Wei, Wentian, Zhe
Work and Grade
- Paper Reflection and Review (30%): Students are expected to read two papers and write one reflection and one review per week. They are due before each class.
- Presentation (30%): Present one or two papers during the semester (depending on the size of the class). You will have roughly three weeks to prepare. Slides are due 8AM of your presentation day.
- Project (30%): Complete a state-of-the-art research project on a topic subject to the instructor's approval. It consists of a mid-term proposal, a final-term presentation and a written report.
- In-Class Discussion (10%): Actively participate in in-class discussion. Try to ask at least one good question each lecture. They are crucial in terms of your final course grade. Don't be shy to speak!
All assignments should be submitted on Blackboard and no late work will be accepted.
Textbooks: There are no required textbooks. We will read papers from CVPR, NIPS etc.
Code of Conduct: Check here for classroom "etiquette" expectations.
Academic honesty: All assignments and activities associated with this course must be performed in accordance with the University of Rochester's Academic Honesty Policy. More information is available at here. You are expected to read, understand and follow the policy.
Disabilities: If you need an accommodation based on the impact of a disability, please contact me privately during the first two weeks to discuss your specific needs. Alternatively, contact Center for Excellence in Teaching and Learning at 585-275-9049 in room 1-154 Dewey Hall to coordinate reasonable accommodations.