Object Classification Seminar


NOTE: Please send requests for lectures between the end of the first meeting until the end of the second meeting. List at least 3 options in decreasing order.

 

Lecture 1 – Introduction  (6/3) 

 

Presenter: Rita Osadchy

Slides: pdf

 

Lecture 2 –TBD   (13/3) 

 

Presenter: Rita Osadchy

Lecture 3 –Instance Recognition    (20/3)   

 

Presenter:

Reading List:

·       Object Recognition from Local Scale-Invariant Features, Lowe, ICCV 1999.  [pdf]  [code] [other implementations of SIFT] [IJCV]

·       Local Invariant Feature Detectors: A Survey, Tuytelaars and Mikolajczyk.  Foundations and Trends in Computer Graphics and Vision, 2008. [pdf]  [Oxford code] [Selected pages -- read pp. 178-188, 216-220, 254-255]

Lecture 4 – Category Recognition 1      (27/3)

 

Presenter:

Reading List:

 

·       Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories, Lazebnik, Schmid, and Ponce, CVPR [pdf], [code],[data].

·       Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, pp.1097—1105 (2012) [pdf] [code (other versions are available)].

Lecture 5 – Category Recognition. Very Deep Networks     (10/04)  

 

Presenter:

Reading Material:

 

Lecture 6–Deep Representations, Transfer Learning        (17/04)

Presenter: 

Slides:

Reading Material:

 

·       J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell: DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. [pdf]

·       http://cs231n.github.io/transfer-learning/

·       G. Koch, R. Zemel, and R. Salakhutdinov Siamese Neural Networks for One-shot Image Recognition [pdf]

 

Lecture 7 – Object Detection (24/04)

Presenter:

Slides:

Reading Material:

·       A Discriminatively Trained, Multiscale, Deformable Part Model, by P. Felzenszwalb,  DMcAllester and D. Ramanan.   CVPR 2008.  [pdf]  [code]

·       Rich feature hierarchies for accurate object detection and semantic segmentation.  R. Girshick et al.  CVPR 2013 [pdf] --  the detection part

Lecture 8 – Attributes and Parts    (1/05)

Presenter:

Slides :

Reading Material:

·        Describing Objects by Their Attributes, A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth, CVPR 2009. [pdf] [web and data]

Lecture 9 – Language and Vision    (8/05) 

Presenter:

Slides :

Reading Material

 

·       Andrej Karpathy Li Fei-Fei. Deep Visual-Semantic Alignments for Generating Image Descriptions CVPR 2015 [pdf] [project]

·       VQA: Visual Question Answering.  Antol et al.  ICCV 2015 [pdf][data/code/demo]

 

Lecture 10 – Faces  (15/05)

Presenter:

Slides:

Reading Material:

 

·        P.N. Belhumeur, J.P. Hespanha, D.J. Kriegman, Eigenfaces vs. Fisherfaces: Recognition using Class Specific Linear Projection, 1996 [pdf]

·        Y. Taigman, M. Yang, M. Ranzato, L.Wolf: DeepFace: Closing the Gap to Human-Level Performance in Face Verification [pdf]

 

Lecture 11 – Video Classification 1  (22/05)     

Presenter:

Slides:

Reading Material:

·        Learning Realistic Human Actions from Movies.  I. Laptev, M. Marszałek, C. Schmid and B. Rozenfeld.  CVPR 2008.  [pdf]  [data] [code]

·        H. Wang, C. Schmid: Action Recognition with Improved Trajectories. ICCV 2013 [pdf]

 

Lecture 12 – Video Classification 2   (29/05)

Presenter:

Slides:

Reading Material:

·        Kapathy et al.: Largescale Video Classification with Convolutional Neural Networks. CVPR 2014  [pdf]

·        K. Simonyan, A. Zissermann: TwoStream Convolutional Networks for Action Recognition in Videos. NIPS 2014 [pdf]

 

Lecture 13 – 3D Scenes and Objects (5/06)

Presenter:

Slides:

Reading Material:

·       Data-Driven 3D Voxel Patterns for Object Category Recognition, Y. Xiang, W. Choi, Y. Lin and S. Savarese,CVPR 2015.  [pdf]  [web/data]

·       Monocular 3D Object Detection for Autonomous Driving. Xiaozhi Chen et. al. [pdf]