Post by yanqing on Apr 25, 2013 2:07:33 GMT -5
Dear students,
Here is some information about the final project.
Firstly, you should form a team (up to 3 persons). Secondly, your team should find an appropriate topic for your project and discuss the duty of each team member. Please email me your topic, the reference paper, and the duty of each member by May 8th, 2013. If your topic is not appropriate, I will suggest you to change another topic. Thirdly, each team should prepare a proposal using PowerPoint. In your proposal, there should be a brief description of what you intend to do, a list of resources you have to help you create your project, and the specific work of each member. This proposal is not a formal one. A file with 3~5 slides is OK. On May 9th, each team will present your proposal in class, and the teacher will give you some advises about your project. Finally, your team should prepare your project. You should submit your report, code, demo and readme file to me by May 22nd.
The details about the final project are listed in our web: 202.120.39.226/Class_page/project.htm.
The topic for your final project should be selected from the newly published papers in ICCV2009, ICCV2011, CVPR2012, CVPR2013, ECCV2010 and ECCV2012. The website of the conferences are listed below, where you can find nearly all the papers of the conference.
Here I also provide some topics for you to choose. The title of each paper is listed below. The information of the source conference and whether there is public code provided is noted at the back of each title. You can select a topic from those ones listed below or find a new one in the six conferences mentioned above. If you meet some problems, you can email me or go to our forum: sjtu-computervision.freeforums.net/ to leave a message.
Lecture 4 Image Enhancement
1. Super-resolution from a single image (ICCV2009)
2. Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation (ICCV2009)
3. Centralized Sparse Representation for Image Restoration (ICCV2011 code)
4. From Learning Models of Natural Image Patches to Whole Image Restoration (ICCV2011 code)
5. Shift-Map Image Editing (ICCV2009)
6. Scene carving: Scene consistent image retargeting (ECCV2010 code)
Lecture 5&6 Feature
1. An HOG-LBP Human Detector with Partial Occlusion Handling (ICCV2009)
2. Human Detection Using Partial Least Squares Analysis (ICCV2009)
3. Part Based Feature Synthesis for Human Detection (ECCV2010 code)
4. Local Intensity Order Pattern for Feature Description (ICCV2011 code)
5. The Shape Boltzmann Machine: a Strong Model of Object Shape (CVPR2012 code)
6. Guided Image Filtering (ECCV2010 code)
7. Adaptive and Generic Corner Detection Based on the Accelerated Segment Test (ECCV2010 code)
8. Rotation invariant non-rigid shape matching in cluttered scenes (ECCV2010 code)
9. Gabor Feature based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary (ECCV2010 code)
10. Coherency Sensitive Hashing (ICCV2011 code)
Lecture 7 Geometry
1. Reconstructing Building Interiors from Images (ICCV2009)
2. Non-Iterative Approach for Fast and Accurate Vanishing Point Detection (ICCV2009 code)
3. A Closed-Form Solution to Uncalibrated Photometric Stereo via Diffuse Maxima (CVPR2012 code)
4. A New Mirror-based Extrinsic Camera Calibration Using an Orthogonality Constraint (CVPR2012 code)
5. 2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds (ECCV2010 code)
6. 3D Reconstruction of a Moving Point from a Series of 2D Projections (ECCV2010 code)
7. Camera Pose Estimation Using First-Order Curve Differential Geometry (ECCV2012 code)
8. Filter Flow (ICCV2009)
9. Motion Interchange Patterns for Action Recognition in Unconstrained Videos (ECCV2010 code)
Lecture 8 Segmentation and Tracking
1. Decomposing a Scene into Geometric and Semantically Consistent Regions (ICCV2009)
2. An efficient algorithm for co-segmentation (ICCV2009)
3. Distributed Cosegmentation via Submodular Optimization on Anisotropic Diffusion (ICCV2011 code)
4. Streaming Hierarchical Video Segmentation (ECCV2012 code)
5. Discrete-Continuous Optimization for Multi-Target Tracking (CVPR2012 code)
6. Distribution Fields for Tracking (CVPR2012 code)
Lecture 9 Learning
1. Sparse Dictionary-based Representation and Recognition of Action Attributes (ICCV2011 code)
2. Sparse Representation or Collaborative Representation: Which Helps Face Recognition (ICCV2011 code)
3. Kernel Null Space Methods for Novelty Detection (CVPR2013 code)
Wish you a good luck!
Amy
Here is some information about the final project.
Firstly, you should form a team (up to 3 persons). Secondly, your team should find an appropriate topic for your project and discuss the duty of each team member. Please email me your topic, the reference paper, and the duty of each member by May 8th, 2013. If your topic is not appropriate, I will suggest you to change another topic. Thirdly, each team should prepare a proposal using PowerPoint. In your proposal, there should be a brief description of what you intend to do, a list of resources you have to help you create your project, and the specific work of each member. This proposal is not a formal one. A file with 3~5 slides is OK. On May 9th, each team will present your proposal in class, and the teacher will give you some advises about your project. Finally, your team should prepare your project. You should submit your report, code, demo and readme file to me by May 22nd.
The details about the final project are listed in our web: 202.120.39.226/Class_page/project.htm.
The topic for your final project should be selected from the newly published papers in ICCV2009, ICCV2011, CVPR2012, CVPR2013, ECCV2010 and ECCV2012. The website of the conferences are listed below, where you can find nearly all the papers of the conference.
www.cvpapers.com/iccv2009.html
www.cvpapers.com/iccv2011.html
www.cvpapers.com/cvpr2012.htm
www.cvpapers.com/cvpr2013.htm
www.cvpapers.com/eccv2010.html
www.cvpapers.com/eccv2012.html
www.cvpapers.com/iccv2011.html
www.cvpapers.com/cvpr2012.htm
www.cvpapers.com/cvpr2013.htm
www.cvpapers.com/eccv2010.html
www.cvpapers.com/eccv2012.html
Here I also provide some topics for you to choose. The title of each paper is listed below. The information of the source conference and whether there is public code provided is noted at the back of each title. You can select a topic from those ones listed below or find a new one in the six conferences mentioned above. If you meet some problems, you can email me or go to our forum: sjtu-computervision.freeforums.net/ to leave a message.
Lecture 4 Image Enhancement
1. Super-resolution from a single image (ICCV2009)
2. Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation (ICCV2009)
3. Centralized Sparse Representation for Image Restoration (ICCV2011 code)
4. From Learning Models of Natural Image Patches to Whole Image Restoration (ICCV2011 code)
5. Shift-Map Image Editing (ICCV2009)
6. Scene carving: Scene consistent image retargeting (ECCV2010 code)
Lecture 5&6 Feature
1. An HOG-LBP Human Detector with Partial Occlusion Handling (ICCV2009)
2. Human Detection Using Partial Least Squares Analysis (ICCV2009)
3. Part Based Feature Synthesis for Human Detection (ECCV2010 code)
4. Local Intensity Order Pattern for Feature Description (ICCV2011 code)
5. The Shape Boltzmann Machine: a Strong Model of Object Shape (CVPR2012 code)
6. Guided Image Filtering (ECCV2010 code)
7. Adaptive and Generic Corner Detection Based on the Accelerated Segment Test (ECCV2010 code)
8. Rotation invariant non-rigid shape matching in cluttered scenes (ECCV2010 code)
9. Gabor Feature based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary (ECCV2010 code)
10. Coherency Sensitive Hashing (ICCV2011 code)
Lecture 7 Geometry
1. Reconstructing Building Interiors from Images (ICCV2009)
2. Non-Iterative Approach for Fast and Accurate Vanishing Point Detection (ICCV2009 code)
3. A Closed-Form Solution to Uncalibrated Photometric Stereo via Diffuse Maxima (CVPR2012 code)
4. A New Mirror-based Extrinsic Camera Calibration Using an Orthogonality Constraint (CVPR2012 code)
5. 2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds (ECCV2010 code)
6. 3D Reconstruction of a Moving Point from a Series of 2D Projections (ECCV2010 code)
7. Camera Pose Estimation Using First-Order Curve Differential Geometry (ECCV2012 code)
8. Filter Flow (ICCV2009)
9. Motion Interchange Patterns for Action Recognition in Unconstrained Videos (ECCV2010 code)
Lecture 8 Segmentation and Tracking
1. Decomposing a Scene into Geometric and Semantically Consistent Regions (ICCV2009)
2. An efficient algorithm for co-segmentation (ICCV2009)
3. Distributed Cosegmentation via Submodular Optimization on Anisotropic Diffusion (ICCV2011 code)
4. Streaming Hierarchical Video Segmentation (ECCV2012 code)
5. Discrete-Continuous Optimization for Multi-Target Tracking (CVPR2012 code)
6. Distribution Fields for Tracking (CVPR2012 code)
Lecture 9 Learning
1. Sparse Dictionary-based Representation and Recognition of Action Attributes (ICCV2011 code)
2. Sparse Representation or Collaborative Representation: Which Helps Face Recognition (ICCV2011 code)
3. Kernel Null Space Methods for Novelty Detection (CVPR2013 code)
Wish you a good luck!
Amy