Lecture Schedule
From cs331b Special Topics in 3dRR
(Difference between revisions)
(21 intermediate revisions not shown) | |||
Line 30: | Line 30: | ||
| Olga Russakovsky and Caleb Jordan | | Olga Russakovsky and Caleb Jordan | ||
| | | | ||
- | 3D detection from D-RGB data: | + | 3D detection from D-RGB data: |
- | [http://www.stanford.edu/class/archive/cs/cs331b/cs331b.1142/wikiupload/c/c0/Lecture3.pdf slides] | + | [http://www.stanford.edu/class/archive/cs/cs331b/cs331b.1142/wikiupload/c/c0/Lecture3.pdf slides] |
*L. Bo, K. Lai, Xiaofeng Ren, and D. Fox "Object Recognition with Hierarchical Kernel Descriptors" [https://homes.cs.washington.edu/~xren/publication/bo_cvpr11_hkdes.pdf link] | *L. Bo, K. Lai, Xiaofeng Ren, and D. Fox "Object Recognition with Hierarchical Kernel Descriptors" [https://homes.cs.washington.edu/~xren/publication/bo_cvpr11_hkdes.pdf link] | ||
Line 43: | Line 43: | ||
| Representing and Recognizing Objects | | Representing and Recognizing Objects | ||
| Guest lecturer: Dr. M. Stark | | Guest lecturer: Dr. M. Stark | ||
- | | 3D object recognition by deformable part models: | + | | |
+ | 3D object recognition by deformable part models: | ||
+ | |||
+ | [http://www.stanford.edu/class/archive/cs/cs331b/cs331b.1142/wikiupload/e/e5/Lecture4.pdf slides] | ||
+ | |||
*B. Pepik, M. Stark, P. Gehler and B. Schiele, "Teaching 3D geometry to deformable part models". CVPR2012 [http://www.d2.mpi-inf.mpg.de/sites/default/files/pepik12cvpr.pdf link] | *B. Pepik, M. Stark, P. Gehler and B. Schiele, "Teaching 3D geometry to deformable part models". CVPR2012 [http://www.d2.mpi-inf.mpg.de/sites/default/files/pepik12cvpr.pdf link] | ||
Line 50: | Line 54: | ||
| 10/7 | | 10/7 | ||
| Representing the 3D Space | | Representing the 3D Space | ||
- | | | + | | |
- | | Large scale 3D reconstruction by structure from motion : | + | Devin LaSalle Guillory and Ziang Xie |
+ | |||
+ | | | ||
+ | Large scale 3D reconstruction by structure from motion : | ||
+ | |||
+ | [http://www.stanford.edu/class/archive/cs/cs331b/cs331b.1142/wikiupload/6/64/Lecture5_2.pdf slides 1] | ||
+ | |||
+ | [http://www.stanford.edu/class/archive/cs/cs331b/cs331b.1142/wikiupload/d/d8/Lecture5.pdf slides 2] | ||
+ | |||
*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 [http://grail.cs.washington.edu/projects/rome/rome_paper.pdf link] | *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 [http://grail.cs.washington.edu/projects/rome/rome_paper.pdf 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 [http://www.cs.illinois.edu/homes/slazebni/publications/eccv10_rome.pdf 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 [http://www.cs.illinois.edu/homes/slazebni/publications/eccv10_rome.pdf link] | ||
Line 59: | Line 71: | ||
| 10/9 | | 10/9 | ||
| Representing the 3D Space | | Representing the 3D Space | ||
- | | | + | | Matt Swaner Vitelli |
| Indoor scene layout reconstruction: | | Indoor scene layout reconstruction: | ||
*D. Lee, T. Kanade, 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] |
+ | *D. Hoiem, A.A. Efros, and M. Hebert, "Geometric Context from a Single Image", ICCV 2005 [http://www.cs.uiuc.edu/~dhoiem/publications/Hoiem_Geometric.pdf link] | ||
|- | |- | ||
Line 68: | Line 81: | ||
| 10/14 | | 10/14 | ||
| Understanding Complex Scenes | | Understanding Complex Scenes | ||
- | | | + | | David Joseph Mandle and Serena Yu-Ching Yeung |
| Joint 3D reconstruction and object detection: | | Joint 3D reconstruction and object detection: | ||
*D. Hoiem, A. Efros, and M. Hebert, "Putting Objects in Perspective". CVPR 2006 [http://www.cs.uiuc.edu/~dhoiem/publications/hoiem_cvpr06.pdf link] | *D. Hoiem, A. Efros, and M. Hebert, "Putting Objects in Perspective". CVPR 2006 [http://www.cs.uiuc.edu/~dhoiem/publications/hoiem_cvpr06.pdf link] | ||
Line 83: | Line 96: | ||
|- | |- | ||
| | | | ||
- | | <span style="color: rgb(255, 0, 0);">'''10/17 | + | | <span style="color: rgb(255, 0, 0);">'''10/17 |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
+ | ''' | ||
Line 113: | Line 119: | ||
| 10/23 | | 10/23 | ||
| Understanding Complex Scenes | | Understanding Complex Scenes | ||
- | | | + | | Kevin Jared Miller |
| | | | ||
Joint segmentation and reconstruction from videos: | Joint segmentation and reconstruction from videos: | ||
Line 124: | Line 130: | ||
| 10/28 | | 10/28 | ||
| Understanding Complex Scenes | | Understanding Complex Scenes | ||
- | | | + | | David Joseph Mandle and Serena Yu-Ching Yeung |
| Joint segmentation and reconstruction from D-RGB data (I): | | 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 [http://cs.nyu.edu/~silberman/papers/indoor_seg_support.pdf link] | *N. Silberman, D. Hoiem, P. Kohli, R. Fergus. "Indoor Segmentation and Support Inference from RGBD Images". ECCV2012 [http://cs.nyu.edu/~silberman/papers/indoor_seg_support.pdf link] | ||
Line 133: | Line 139: | ||
| 10/30 | | 10/30 | ||
| Understanding Complex Scenes | | Understanding Complex Scenes | ||
- | | | + | | Kevin Jared Miller and Caleb Stephen Jordan |
| Joint segmentation and reconstruction from D-RGB data (II): | | Joint segmentation and reconstruction from D-RGB data (II): | ||
*D. Munoz, J. Bagnell, and M. Hebert. "Stacked Hierarchical Labeling". ECCV2010 [http://www.ri.cmu.edu/pub_files/2010/9/munoz_eccv_10.pdf link] | *D. Munoz, J. Bagnell, and M. Hebert. "Stacked Hierarchical Labeling". ECCV2010 [http://www.ri.cmu.edu/pub_files/2010/9/munoz_eccv_10.pdf link] | ||
Line 147: | Line 153: | ||
|- | |- | ||
- | | | + | | 15 |
- | | <span style="color: rgb( | + | | |
- | + | <span style="color: rgb(0, 0, 255);">'''11/4'''</span> | |
- | + | ||
+ | | Understanding Human Activities | ||
+ | | Sam James Corbett-Davies and Christopher Choy and Kyunghee Kim | ||
+ | | Human pose estimation and activity recognition from D-RGB <span style="line-height: 1.5em;">data:</span> | ||
+ | *Tutorial on Randomized decision trees and forests [http://www.iis.ee.ic.ac.uk/~tkkim/iccv09_tutorial link] | ||
+ | *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 [http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf link] | ||
+ | *J. Wang, Z. Liu, Y. Wu, and J. Yuan. "Mining Actionlet Ensemble for Action Recognition with Depth Cameras". [http://research.microsoft.com/en-us/um/people/zliu/papers/joint_modeling_final.pdf link] | ||
+ | |- | ||
+ | | | ||
+ | | <span style="color: rgb(255, 0, 0);">'''11/5''' | ||
</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 159: | Line 173: | ||
|- | |- | ||
| 14 | | 14 | ||
- | | 11/6 | + | | |
+ | 11/6 | ||
+ | |||
| Understanding Human Pose | | Understanding Human Pose | ||
- | | | + | | Vivardhan Kanoria and Devin LaSalle Guillory |
| Human pose estimation and activity recognition from 2D <span style="line-height: 1.5em;">images:</span> | | Human pose estimation and activity recognition from 2D <span style="line-height: 1.5em;">images:</span> | ||
*L. Bourdev, and J. Malik. "Poselets: Body Part 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 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 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 Activations". ECCV2010 [http://www.cs.berkeley.edu/~lbourdev/poselets/poselets-eccv10.pdf link] | ||
*B. Yao and L. Fei-Fei. "Action Recognition with Exemplar Based 2.5D Graph Matching". ECCV2012 [http://vision.stanford.edu/documents/YaoFei-Fei_ECCV12.pdf link] | *B. Yao and L. Fei-Fei. "Action Recognition with Exemplar Based 2.5D Graph Matching". ECCV2012 [http://vision.stanford.edu/documents/YaoFei-Fei_ECCV12.pdf link] | ||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
|- | |- | ||
Line 188: | Line 194: | ||
|- | |- | ||
| 17 | | 17 | ||
- | | 11/ | + | | |
+ | '''<span style="color: rgb(0, 0, 255);">11/11 </span>''' | ||
+ | |||
+ | '''<span style="color: rgb(0, 0, 255);">7pm </span>''' | ||
+ | |||
+ | '''<span style="color: rgb(0, 0, 255);">380-380c</span>''' | ||
+ | |||
| Understanding Human Activities | | Understanding Human Activities | ||
- | | | + | | Sam James Corbett-Davies and Vivardhan Kanoria |
| Joint estimation of object/scene affordances and human activities (I):<br> | | 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] | ||
Line 197: | Line 209: | ||
|- | |- | ||
| 18 | | 18 | ||
- | | | + | | 11/13 |
| Understanding Human Activities | | Understanding Human Activities | ||
- | | | + | | Christopher Choy and Ziang Xie and Kyunghee Kim |
| Joint estimation of object/scene affordances and human activities (II):<br> | | Joint estimation of object/scene affordances and human activities (II):<br> | ||
*V. Delatitre, D. Fouhey, I. Laptec, Sivic, A. Gupta, and A. A. Efros. "Scene semantics from long term observation of 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 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 geometry to Human workspace". CVPR2011 [http://graphics.cs.cmu.edu/projects/peopleWatching/dfouhey_people.pdf link] | + | *A. Gupta, S. Satkin, A. A. Efros, and M. Hebert. "From 3D scene geometry to Human workspace". CVPR2011 [http://www.cs.cmu.edu/~abhinavg/papers/0586.pdf link]<br> |
+ | *D. Fouhey, V. Delaitre, A. Gupta, A. A. Efros, I. Laptev, and J. Sivic. "People Watching: Human Actions as a Cue for Single View Geometry". ECCV2012 [http://graphics.cs.cmu.edu/projects/peopleWatching/dfouhey_people.pdf link] | ||
|- | |- | ||
- | | '''<span style="color: rgb(255, 0, 0);"> | + | | '''<br>''' |
- | + | | '''<span style="color: rgb(255, 0, 0);"> </span>'''11/18'''<span style="color: rgb(255, 0, 0);"> </span><br>''' | |
- | | '''<span style="color: rgb(255, 0, 0);"> | + | | '''<span style="color: rgb(255, 0, 0);"> </span>'''no class'''<br>''' |
| | | | ||
| | | | ||
|- | |- | ||
- | | ''' | + | | '''<br>''' |
- | | '''<span style="color: rgb(255, 0, 0);"> | + | | '''<span style="color: rgb(255, 0, 0);"> </span>'''11/20'''<span style="color: rgb(255, 0, 0);"> </span><br>''' |
- | + | | no class | |
| | | | ||
| | | | ||
Line 229: | Line 242: | ||
| | | | ||
|- | |- | ||
- | | | + | | <span style="color: rgb(255, 0, 0);">''' 19'''</span> |
- | | 12/2 | + | | <span style="color: rgb(255, 0, 0);">''' 12/2 |
+ | |||
+ | ''' | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | </span> | ||
| | | | ||
- | + | <span style="color: rgb(255, 0, 0);">'''Final Project Presentations''' | |
+ | </span><br> | ||
- | | | + | | <span style="color: rgb(255, 0, 0);">''' |
- | | | + | |
+ | |||
+ | ''' | ||
+ | |||
+ | </span> | ||
+ | | <span style="color: rgb(255, 0, 0);">''' ''' | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | </span> | ||
|- | |- | ||
- | | | + | | <span style="color: rgb(255, 0, 0);">''' 20'''</span> |
- | | 12/ | + | | |
- | | | + | <span style="color: rgb(255, 0, 0);">'''12/2'''</span> |
- | | | + | |
+ | <span style="color: rgb(255, 0, 0);">'''7pm @ Gates 219'''</span> | ||
+ | |||
+ | | | ||
+ | <span style="color: rgb(255, 0, 0);">''' Final Project Presentations'''</span> | ||
+ | |||
+ | | <span style="color: rgb(255, 0, 0);">''' '''</span> | ||
| | | | ||
|- | |- | ||
| | | | ||
- | | | + | | |
- | | | + | 12/4<br> |
+ | |||
+ | | no class due to ICCV | ||
| | | | ||
| | | | ||
|- | |- | ||
| | | | ||
- | | | + | | '''<span style="color: rgb(255, 0, 0);">12/13</span>''' |
- | | | + | | <span style="color: rgb(255, 0, 0);">''' Final Project Report Due'''</span> |
| | | | ||
| | | |
Latest revision as of 15:32, 12 November 2013
Lect. | Date | Topics | Presenter | Paper/Slides |
---|---|---|---|---|
1 | 9/23 | Introductions | lecture slides | |
2 | 9/25 | Representing and Recognizing Objects | Guest lecturer: Y. Xiang |
3D object recognition by aspect graph-based models:
|
3 | 9 /30 | Representing and Recognizing Objects | Olga Russakovsky and Caleb Jordan |
3D detection from D-RGB data:
|
4 | 10/2 | Representing and Recognizing Objects | Guest lecturer: Dr. M. Stark |
3D object recognition by deformable part models:
|
5 | 10/7 | Representing the 3D Space |
Devin LaSalle Guillory and Ziang Xie |
Large scale 3D reconstruction by structure from motion :
|
6 | 10/9 | Representing the 3D Space | Matt Swaner Vitelli | Indoor scene layout reconstruction: |
7 | 10/14 | Understanding Complex Scenes | David Joseph Mandle and Serena Yu-Ching Yeung | Joint 3D reconstruction and object detection: |
8 | 10/16 | Understanding Complex Scenes | Guest lecturer: B. Kim | 2D/3D CRF models for scene understanding:
|
10/17
| Project Proposal due | |||
9 | 10/21 | Understanding Complex Scenes | Guest lecturer: Y. Bao | Semantic structure from motion:
|
10 | 10/23 | Understanding Complex Scenes | Kevin Jared Miller |
Joint segmentation and reconstruction from videos: |
11 | 10/28 | Understanding Complex Scenes | David Joseph Mandle and Serena Yu-Ching Yeung | Joint segmentation and reconstruction from D-RGB data (I): |
12 | 10/30 | Understanding Complex Scenes | Kevin Jared Miller and Caleb Stephen Jordan | Joint segmentation and reconstruction from D-RGB data (II): |
13 | 11/4 | Understanding Human Pose | Guest lecturer: Dr. Roland Angst | Joint segmentation and reconstruction from D-RGB data (III):
|
15 |
11/4 | Understanding Human Activities | Sam James Corbett-Davies and Christopher Choy and Kyunghee Kim | Human pose estimation and activity recognition from D-RGB data:
|
11/5 | Project Mid-term Report due | |||
14 |
11/6 | Understanding Human Pose | Vivardhan Kanoria and Devin LaSalle Guillory | Human pose estimation and activity recognition from 2D images:
|
16 | 11/11 | Understanding Human Activities | Guest lecturer: Dr. W. Choi | Recognizing collective activities: |
17 |
11/11 7pm 380-380c | Understanding Human Activities | Sam James Corbett-Davies and Vivardhan Kanoria | Joint estimation of object/scene affordances and human activities (I): |
18 | 11/13 | Understanding Human Activities | Christopher Choy and Ziang Xie and Kyunghee Kim | Joint estimation of object/scene affordances and human activities (II):
|
| 11/18 | no class | ||
| 11/20 | no class | ||
11/25 | no class - Thanksgiving Break | |||
11/27 | no class - Thanksgiving Break | |||
19 | 12/2
|
Final Project Presentations
|
|
|
20 |
12/2 7pm @ Gates 219 |
Final Project Presentations | ||
12/4 | no class due to ICCV | |||
12/13 | Final Project Report Due | |||