| Lect.
| Date
| Topics
| Presenter
| Paper/Slides
|
| 1
| 9/23
| Introductions
|
| slides
|
| 2
| 9/25
| Representing and Recognizing Objects
| Guest lecturer: Y. Xiang
|
3D object recognition by aspect graph-based models:
- Y.Xiang and S.Savarese. "Estimating the aspect layout of object categories". CVPR2012 link
|
| 3
| 9 /30
| Representing and Recognizing Objects
|
| 3D detection from D-RGB data:
- L. Bo, K. Lai, Xiaofeng Ren, and D. Fox "Object Recognition with Hierarchical Kernel Descriptors" link
- L. Bo, X. Ren, and D. Fox. "Kernel Descriptors for Visual Recognition". NIPS, December 2010 link
- K. Lai, L. Bo, X. Ren, and D. Fox. "A Large-Scale Hierarchical Multi-View RGB-D Object Dataset". IEEE International Conference on on Robotics and Automation, 2011 link
|
| 4
| 10/2
| Representing and Recognizing Objects
| Guest lecturer: Dr. M. Stark
| 3D object recognition by deformable part models:
- B. Pepik, M. Stark, P. Gehler and B. Schiele, "Teaching 3D geometry to deformable part models". CVPR2012 link
|
| 5
| 10/7
| Representing the 3D Space
|
| Large scale 3D reconstruction by structure from motion :
- S. Agarwal, Y. Furukawa, N. Snavely, I. Simon, B. Curless, S. Seitz and R. Szeliski. Communications of the ACM, Vol. 54, No. 10, Pages 105-112, October 2011 link
- J. Frahm, P. Georgel, D. Gallup, T. Johnson, R. Raguram, C. Wu, Y. Jen, E. Dunn, B. Clipp, S. Lazebnik, and M. Pollefeys. "Building Rome on a Cloudless Day". ECCV2010 link
|
| 6
| 10/9
| Representing the 3D Space
|
| Indoor scene layout reconstruction:
- D. Lee, T. Kanade, and M. Hebert. "3D Scene Analysis". CVPR2009 link
- A. Schwing and R. Urtasun. "Efficient Exact Inference for 3D Indoor Scene Understanding". ECCV2012 link
|
| 7
| 10/14
| Understanding Complex Scenes
|
| Joint 3D reconstruction and object detection:
- D. Hoiem, A. Efros, and M. Hebert, "Putting Objects in Perspective". CVPR 2006 link
- V. Hedau, D. Hoiem, and D. Forsyth. "Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry". ECCV 2010 link
|
| 8
| 10/16
| Understanding Complex Scenes
| Guest lecturer: B. Kim
| 2D/3D CRF models for scene understanding:
- B. Kim, M. Sun ,P. Kohli, and S. Savarese. "Relating things and stuff by High-Order Poterntial modeling". ECCV2012 link
|
|
| 10/17
| Project Proposal due
|
|
|
| 9
| 10/21
| Understanding Complex Scenes
| Guest lecturer: Y. Bao
| Semantic structure from motion:
- S. Bao and S. Savarese, "Semantic Structure from Motion". CVPR2011 link
|
| 10
| 10/23
| Understanding Complex Scenes
|
|
Joint segmentation and reconstruction from videos:
- Tutorial on MCMC
- C. Wojek, S. Roth, K. Schindler, B. Schiele. "Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes". link
|
| 11
| 10/28
| Understanding Complex Scenes
|
| Joint segmentation and reconstruction from D-RGB data (I):
- N. Silberman, D. Hoiem, P. Kohli, R. Fergus. "Indoor Segmentation and Support Inference from RGBD Images". ECCV2012 link
- S. Gupta, P. Arbelaez, and J. Malik. "Perceptual Organization and Recognition of Indoor Scenes from RGBD Images". CVPR2013 (oral). link
|
| 12
| 10/30
| Understanding Complex Scenes
|
| Joint segmentation and reconstruction from D-RGB data (II):
- D. Munoz, J. Bagnell, and M. Hebert. "Stacked Hierarchical Labeling". ECCV2010 link
- D. Munoz, J. Bagnell, and M. Hebert. "Co-inference for Multi-modal Scene Analysis". ECCV2012 link
|
| 13
| 11/4
| Understanding Human Pose
| Guest lecturer: Dr. Roland Angst
| Joint segmentation and reconstruction from D-RGB data (III):
- C. Häne, C. Zach, A. Cohen, R. Angst, and M. Pollefeys. "Joint 3D scene reconstruction and class segmentation". link
|
|
| 11/5
| Project Mid-term Report due
|
|
|
| 14
| 11/6
| Understanding Human Pose
|
| Human pose estimation and activity recognition from 2D images:
- L. Bourdev, and J. Malik. "Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations". ICCV2009 link
- L. Bourdev, S. Maji, T. Brox, and J. Malik. "Detecting People Using Mutually Consistent Poselet Activations". ECCV2010 link
- B. Yao and L. Fei-Fei. "Action Recognition with Exemplar Based 2.5D Graph Matching". ECCV2012 link
|
| 15
| tba
| Understanding Human Activities
|
| Human pose estimation and activity recognition from D-RGB data:
- Tutorial on Randomized decision trees and forests
- J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake. "Real Time human pose recognition in parts from single depth image". CVPR2011 link
- J. Wang, Z. Liu, Y. Wu, and J. Yuan. "Mining Actionlet Ensemble for Action Recognition with Depth Cameras". link
|
| 16
| 11/11
| Understanding Human Activities
| Guest lecturer: Dr. W. Choi
| Recognizing collective activities:
- W. Choi, K. Shahid, and S. Savarese "What are they doing?: Collective Activity Classification Using Spatio-Temporal Relationship Among People". VSWS2009 and ICCV2009 link
- W. Choi and S. Savarese "A Unified Framework for MultiTarget Tracking and Collective Activity Recognition". ECCV2012 link
|
| 17
| 11/13
| Understanding Human Activities
|
| Joint estimation of object/scene affordances and human activities (I):
- J. Gall, A. Fossati, and L. van Gool. (2011). "Functional Categorization of Objects Using Real-Time Markerless Motion Capture". CVPR2011 link
- H. Koppula, R. Gupta, and A. Saxena. "Learning Human Activities and Object Affordances from RGB-D Videos". IJRR2013 link
|
| 18
| tba
| Understanding Human Activities
|
| Joint estimation of object/scene affordances and human activities (II):
- V. Delatitre, D. Fouhey, I. Laptec, Sivic, A. Gupta, and A. A. Efros. "Scene semantics from long term observation of people". ECCV2012 link
- A. Gupta, S. Satkin, A. A. Efros, and M. Hebert. "From 3D scene geometry to Human workspace". CVPR2011 link
|
19
| 11/18
| Final Project Presentations
|
|
|
20
| 11/20
| Final Project Presentations
|
|
|
|
| 11/25
| no class - Thanksgiving Break
|
|
|
|
| 11/27
| no class - Thanksgiving Break
|
|
|
|
| 12/2
|
no class due to ICCV
|
|
|
|
| 12/4
| no class due to ICCV
|
|
|
|
| 12/13
| Final Project Report Due
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
