Lecture Schedule

From cs331b Special Topics in 3dRR

(Difference between revisions)
Jump to: navigation, search
Line 55: Line 55:
|    
|    
| Indoor scene layout reconstruction:  
| Indoor scene layout reconstruction:  
-
*D. Lee, T. Kanadem, and M. Hebert. "3D Scene Analysis". CVPR2009 [http://www.cs.cmu.edu/~dclee/pub/cvpr09lee.pdf link]  
+
*D. Lee, T. Kanade, and M. Hebert. "3D Scene Analysis". CVPR2009 [http://www.cs.cmu.edu/~dclee/pub/cvpr09lee.pdf link]  
*A. Schwing and R. Urtasun. "Efficient Exact Inference for 3D Indoor Scene Understanding". ECCV2012 [http://www.alexander-schwing.de/papers/SchwingEtAl_ECCV2012.pdf link]
*A. Schwing and R. Urtasun. "Efficient Exact Inference for 3D Indoor Scene Understanding". ECCV2012 [http://www.alexander-schwing.de/papers/SchwingEtAl_ECCV2012.pdf link]
Line 72: Line 72:
| Understanding Complex Scenes  
| Understanding Complex Scenes  
| Guest lecturer: B. Kim  
| Guest lecturer: B. Kim  
-
| 2D/3D CRF models fo understanding:  
+
| 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 [http://cvgl.stanford.edu/papers/kim_hipotws_eccv12.pdf link]
*B. Kim, M. Sun ,P. Kohli, and S. Savarese. "Relating things and stuff by High-Order Poterntial modeling". ECCV2012 [http://cvgl.stanford.edu/papers/kim_hipotws_eccv12.pdf link]
|-
|-
|    
|    
-
| <span style="color: rgb(255, 0, 0);">'''10/17&nbsp;
+
| <span style="color: rgb(255, 0, 0);">'''10/17&nbsp;'''
-
'''
+
 
 +
 
 +
 
 +
 
 +
 
 +
 
</span>
</span>
Line 97: Line 102:
| Understanding Complex Scenes  
| Understanding Complex Scenes  
| &nbsp;  
| &nbsp;  
-
| Tutorial on MCMC:
+
|  
 +
Joint segmentation and reconstruction from videos:
 +
 
 +
*Tutorial on MCMC
*C. Wojek, S. Roth, K. Schindler, B. Schiele.&nbsp;"Monocular 3D Scene Modeling and Inference: Understanding&nbsp;Multi-Object Traffic Scenes". [http://domino.mpi-inf.mpg.de/intranet/d2/d2publ.nsf/0/ac2eb7bd29ab4279c12578110057e2d9/$FILE/wojek2010eccv.pdf link]
*C. Wojek, S. Roth, K. Schindler, B. Schiele.&nbsp;"Monocular 3D Scene Modeling and Inference: Understanding&nbsp;Multi-Object Traffic Scenes". [http://domino.mpi-inf.mpg.de/intranet/d2/d2publ.nsf/0/ac2eb7bd29ab4279c12578110057e2d9/$FILE/wojek2010eccv.pdf link]
Line 129: Line 137:
| &nbsp;  
| &nbsp;  
| <span style="color: rgb(255, 0, 0);">'''11/5'''&nbsp;
| <span style="color: rgb(255, 0, 0);">'''11/5'''&nbsp;
 +
 +
 +
 +
</span>
</span>
| <span style="color: rgb(255, 0, 0);">''' Project Mid-term Report due'''</span>  
| <span style="color: rgb(255, 0, 0);">''' Project Mid-term Report due'''</span>  
Line 138: Line 150:
| Understanding Human Pose  
| Understanding Human Pose  
| &nbsp;  
| &nbsp;  
-
| Human pose estimation and activity recognition from 2D  
+
| Human pose estimation and activity recognition from 2D&nbsp;<span style="line-height: 1.5em;">images:</span>
-
images:  
+
-
 
+
*L. Bourdev, and J. Malik. "Poselets: Body Part&nbsp;Detectors Trained Using 3D Human Pose Annotations". ICCV2009 [http://www.eecs.berkeley.edu/Research/Projects/CS/vision/human/poselets_iccv09.pdf link]  
*L. Bourdev, and J. Malik. "Poselets: Body Part&nbsp;Detectors Trained Using 3D Human Pose Annotations". ICCV2009 [http://www.eecs.berkeley.edu/Research/Projects/CS/vision/human/poselets_iccv09.pdf link]  
*L. Bourdev, S. Maji, T. Brox, and J. Malik. "Detecting People Using Mutually Consistent Poselet&nbsp;Activations". ECCV2010 [http://www.cs.berkeley.edu/~lbourdev/poselets/poselets-eccv10.pdf link]  
*L. Bourdev, S. Maji, T. Brox, and J. Malik. "Detecting People Using Mutually Consistent Poselet&nbsp;Activations". ECCV2010 [http://www.cs.berkeley.edu/~lbourdev/poselets/poselets-eccv10.pdf link]  
Line 150: Line 160:
| Understanding Human Activities  
| Understanding Human Activities  
| &nbsp;  
| &nbsp;  
-
| Human pose estimation and activity recognition from D-RGB  
+
| Human pose estimation and activity recognition from D-RGB&nbsp;<span style="line-height: 1.5em;">data:</span>
-
data:  
+
-
 
+
*Tutorial on Randomized decision trees and forests  
*Tutorial on Randomized decision trees and forests  
*J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp,&nbsp;M. Finocchio, R. Moore, A. Kipman, and A. Blake. "Real Time human pose recognition in parts from single&nbsp;depth image". CVPR2011 [http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf link]  
*J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp,&nbsp;M. Finocchio, R. Moore, A. Kipman, and A. Blake. "Real Time human pose recognition in parts from single&nbsp;depth image". CVPR2011 [http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf link]  
Line 171: Line 179:
| Understanding Human Activities  
| Understanding Human Activities  
| &nbsp;  
| &nbsp;  
-
|  
+
| Joint estimation of object/scene affordances and human activities (I):<br>
*J. Gall, A. Fossati, and L. van Gool. (2011). "Functional Categorization of Objects Using Real-Time Markerless Motion Capture". CVPR2011 [http://www.vision.ee.ethz.ch/~gallju/download/jgall_dynamiccat_cvpr11.pdf link]  
*J. Gall, A. Fossati, and L. van Gool. (2011). "Functional Categorization of Objects Using Real-Time Markerless Motion Capture". CVPR2011 [http://www.vision.ee.ethz.ch/~gallju/download/jgall_dynamiccat_cvpr11.pdf link]  
*H. Koppula, R. Gupta, and A. Saxena.&nbsp;"Learning Human Activities and Object Affordances from&nbsp;RGB-D Videos". IJRR2013 [http://arxiv.org/pdf/1210.1207v2.pdf link]<br>
*H. Koppula, R. Gupta, and A. Saxena.&nbsp;"Learning Human Activities and Object Affordances from&nbsp;RGB-D Videos". IJRR2013 [http://arxiv.org/pdf/1210.1207v2.pdf link]<br>
Line 180: Line 188:
| Understanding Human Activities  
| Understanding Human Activities  
| &nbsp;  
| &nbsp;  
-
| Joint estimation of object/scene affordances and human  
+
| Joint estimation of object/scene affordances and human activities (II):<br>
-
pose:  
+
-
 
+
*V. Delatitre, D. Fouhey, I. Laptec, Sivic, A. Gupta, and A. A. Efros. "Scene semantics from long term observation of&nbsp;people". ECCV2012 [http://repository.cmu.edu/cgi/viewcontent.cgi?article=1775&context=robotics link]  
*V. Delatitre, D. Fouhey, I. Laptec, Sivic, A. Gupta, and A. A. Efros. "Scene semantics from long term observation of&nbsp;people". ECCV2012 [http://repository.cmu.edu/cgi/viewcontent.cgi?article=1775&context=robotics link]  
*A. Gupta, S. Satkin, A. A. Efros, and M. Hebert. "From 3D scene&nbsp;geometry to Human workspace". CVPR2011 [http://graphics.cs.cmu.edu/projects/peopleWatching/dfouhey_people.pdf link]<br>
*A. Gupta, S. Satkin, A. A. Efros, and M. Hebert. "From 3D scene&nbsp;geometry to Human workspace". CVPR2011 [http://graphics.cs.cmu.edu/projects/peopleWatching/dfouhey_people.pdf link]<br>

Revision as of 16:02, 26 September 2013

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    
         
         
         
         



Personal tools