CVAP Computer Vision Seminars
Fridays, 13:30 - 15:00
Teknikringen 14, Room 304

Notes | | Scheduled Talks | | Previous Talks | | Candidate Papers | | Upcoming events |


Schedueled future talks

Date Presenter Title/Description Materials

Previous talks

Date Presenter Title/Description Materials
22/05/2015 Ali Sharif Razavian J. Weston, S. Chopra, A. Bordes "Memory Networks" In ICLR 2015
10/04/2015 Roelof Pieters F. Hill, A. Korhonen, K. Cho, Y. Bengio "Learning to Understand Phrases by Embedding the Dictionary" In arXiv 2015
27/03/2015 Hossein Azizpour Xiao Lin, Devi Parikh "Dont Just Listen, Use Your Imagination:Leveraging Visual Common Sense for Non-Visual Tasks" In CVPR 2015
13/03/2015 Amaru Cuba Gyllensten Zhang and LeCun "Text Understanding from Scratch" In arXiv 2015
20/02/2015 Roelof Pieters
Ali Sharif Razavian
R. Socher, M. Ganjoo, H. Sridhar, O. Bastani, C. Manning, and A. Ng. "Zero-shot learning through cross-modal transfer." In ICLR 2013
A. Frome, G. S. Corrado, J. Shlens, S. Bengio, J. Dean, T. Mikolov "Devise: A deep visual-semantic embeddingmodel." In NIPS, 2013
13/02/2015 Yang Zhong Y. Sun, X. Wang, and X. Tang "Deep Learning Face Representation from Predicting 10,000 Classes." CVPR 2014
Y. Sun, X. Wang, and X. Tang "Deep Learning Face Representation by Joint Identification-Verification." arXiv 2014
Y. Sun, X. Wang, and X. Tang "Deeply Learned Face Representations are Sparse, Selective, and Robust." arXiv 2014
06/02/2015 Hossein Azizpour Andrej Karpathy, Li Fei-Fei "Deep Visual-Semantic Alignments for Generating Image Descriptions" arXiv 2014 Project Page
10/10/2014 Tim Cootes, Manchester University (Invited Talk) Extracting the shape of structures in medical images
10/10/2014 Adrian Hilton, University of Surrey (Invited Talk) 4D Vision: Performance Capture for Human Movement Analysis & Animation
12/06/2014 Josef Sivic, INRIA/ENS Paris (Invited Talk) Learning mid-level image representations for visual recognition
12/06/2014 Cristian Sminchisescu, Lund University (Invited Talk) Iterated Second-order Label Sensitive Pooling for 3D Human Pose Estimation
27/05/2014 Vahid Kazemi Adam Coates, Honglak Lee, and Andrew Ng "An Analysis of Single-Layer Networks in Unsupervised Feature Learning" AI Statistics 2011
23/05/2014 Pawan Kumar, Ecole Centrale Paris, INRIA Saclay (Invited Talk for SAIS Workshop) Multiplicative Bounds for Metric Labeling
22/05/2014 Karteek Alahari, INRIA Grenoble Rhone-Alpes (Invited Talk) Scene Understanding: What more can we do with videos, depth and text?
20/05/2014 Hossein Azizpour K. Chatfield, K. Simonyan, A. Vedaldi, A. Zisserman "Return of the Devil in the Details: Delving Deep into Convolutional Nets" arXiv 2014
20/05/2014 Bodo Rosenhahn, Leibniz Universität Hannover, Germany (Invited Talk) Human Motions and Multi-People Tracking
06/05/2014 Oscar Danielsson Christian Szegedy et al. "Intriguing properties of neural networks" ICLR 2014
30/04/2014 Atsuto Maki Shuiwang Ji, et al. "3D Convolutional Neural Networks for Human Action Recognition" PAMI 2013
Andrej Karpathy et al. "Large-scale Video Classification with Convolutional Neural Networks" CVPR 2014
22/04/2014 Josephine Sullivan
Hossein Azizpour
Stochastic Gradient Methods with a focus on Hogwild
R. Girshick et al. "Rich feature hierarchies for accurate object detection and semantic segmentation" updated arXiv report
15/04/2014 Hossein Azizpour Our future tracks for Deep Learning
01/04/2014 Vahid Kazemi
Oscar Danielsson
Hossein Azizpour
1) Y. Taigman, M. Yang, M. Ranzato, L. Wolf "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" CVPR 2014
2) A. Toshev, C. Szegedy "DeepPose: Human Pose Estimation via Deep Neural Networks" CVPR 2014
3) N. Zhang, M. Paluri, M. Ranzato, T. Darrell, L. Bourdev "PANDA: Pose Aligned Networks for Deep Attribute Modeling" CVPR 2014
1)Slides PPT
2)Slides PDF
2)Slides PDF
25/03/2014 Heydar Maboudi Bengio et al. "Representation Learning: A Review and New Perspectives" PAMI 2013
24/03/2014 Iasonas Kokkinos, Ecole Centrale Paris (Invited Talk) Fast and Exact Algorithms for Object Detection with Deformable Models.
18/03/2014 Hossein Azizpour Deep Representation as Baseline for All Recognition Tasks Slides PDF
21/1/2014 Pascal Fua, EPFL (Invited Talk) Indentity Preserving Multi-People Tracking through Linear Programming
13/12/2013 Vahid Kazemi
Hossein Azizpour
1) M. Zeiler and R. Fergus, "Visualizing and Understanding Convolutional Networks", TR 2013
2) R. Girshick, J. Donahue, T. Darrell, and J. Malik "Rich feature hierarchies for accurate object detection and semantic segmentation", TR 2013
3) M. Oquab, L. Bottou, I. Laptev and J. Sivic "Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks", TR 2013
with a discussion about recent developments in deep learning for computer vision
2-3)Slides PDF
2-3)Slides PPT
11/11/2013 Miroslav Kobetski Addressing occlusion in wearable videos
25/10/2013 Heydar Maboudi M. Juneja, A. Vedaldi, C. Jawahar, A. Zisserman. "Blocks that Shout: Distinctive Parts for Scene Classification" CVPR 2013
18/10/2013 1) Ali Sharif Razavian
2) Hossein Azizpour
1) C. Vondrick, A. Khosla, T. Malisiewicz, A. Torralba. "HOGgles: Visualizing Object Detection Features", ICCV 2013
2) Xiaofeng Ren and Deva Ramanan "Histograms of Sparse Codes for Object Detection", CVPR 2013

2)Slides PDF
04/10/2013 Omid Aghazadeh One class SVMs and an extension to it (ongoing research)
06/09/2013 Cristian Sminchisescu, Lund University (Invited Talk) Figure-Ground Segmentation and Pooling for Visual Scene Analysis
14/06/2013 Magnus Burenius Gu et al. "Linear time offline tracking and lower envelope algorithms", ICCV 2011
31/05/2013 Miroslav Kobetski A. Prest, Ch. Leistner, J. Civera, C. Schmid and V. Ferrari, "Learning Object Class Detectors from Weakly Annotated Video", CVPR 2012
24/05/2013 Ali Sharif Razavian R. Arandjelovic. A. Zisserman, "All About VLAD", CVPR 2013
with a summary of H. Jegou, M. Douze, C. Schmid, P. Pérez, "Aggregating local descriptors into a compact image representation", CVPR 2010
17/05/2013 Josephine Sullivan Rodrigo Quian Quiroga, "Concept cells: the building blocks of declarative memory functions", Nature Neuroscience 2012
with an Introduction to Brain Cells and Their Functionalities
13/05/2013 Trevor Darrell, UC Berkeley (Invited Talk) Efficient large-scale visual category recognition
08/05/2013 Hossein Azizpour N. Razavi, J. Gall, P. Kohli, L. Van Gool "Latent Hough Transform for Object Detection", ECCV 2012
with a glance at:
B. Leibe, A. Leonardis, B. Schiele. "Robust Object Detection with Interleaved Categorization and Segmentation", IJCV 2008
Gall J., Yao A., Razavi N., van Gool L., and Lempitsky V., "Hough Forests for Object Detection, Tracking, and Action Recognition" PAMI 2011
Barinova O, Lempitsky V, Kohli P. "On detection of multiple object instances using Hough transform", PAMI 2012
24/04/2013 Horesh Ben Shitrit, EPFL (Invited Talk) Multi-Camera People Identification and Tracking.
22/03/2013 Magnus Burénius Vedaldi, Blaschko, Zisserman. "Learning Equivariant Structured Output SVM Regressors", ICCV 2011 Slides PDF
15/03/2013 Miroslav Kobetski L. Liu, L. Wang, "What Has My Classifier Learned? Visualizing the Classification Rules of Bag-of-Feature Model by Support Region Detection." CVPR 2012
D. Hoiem, Y. Chodpathumwan, and Q. Dai, "Diagnosing Error in Object Detectors", ECCV 2012
Discussion on the relevance of the current performance evaluation criteria
8/03/2013 Vahid Kazemi S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, P. Kohli, "Decision Tree Fields", ICCV 2011 Slides PDF
1/03/2013 Omid Aghazadeh McFee and Lanckriet, "Metric Learning to Rank" ICML 2010
Plus an introduction on metric learning
22/02/2013 Ali Sharifrazavian General discussion on deep learning and the impact of "Drop Out" technique
suggested reading: Hinton et al. Improving neural networks by preventing co-adaptation of feature detectors
19/02/2013 Heydar Maboudi W. Yang, Y. Wang, A. Vahdat, and G. Mori. "Kernel Latent SVM for Visual Recognition", NIPS 2012
Discussion on representation with simple classifiers vs. non-linear classifiers working on simple features
08/02/2013 Hossein Azizpour 1) L. Ladicky, P. H. S. Torr, A. Zisserman. "Latent SVMs for Human Detection with a Locally Affine Deformation Field" BMVC 2012
2) A. Vedaldi, V. Gulshan, M. Varma, and A. Zisserman. "Multiple Kernels for Object Detection." ICCV 2009
3) X. Zhu, C. Vondrick, D. Ramanan, C. Fowlkes, "Do We Need More Training Data or Better Models for Object Detection?" BMVC 2012
Discussion on nonlinear classification vs model design and big data vs model design
1)Slides PPT
2)Slides PDF
3)Slides PDF
01/02/2013 Magnus Burénius Introduction to Structure SVM and Rank SVM with a look at
M. Blaschko, and C. H. Lampert. "Learning to Localize Objects with Structured Output Regression, ECCV 2008
Slides PDF
07/12/2012 Ali Sharif Razavian A. Krizhevsky, I. Sutskever, G. E. Hinton. "ImageNet Classification with Deep Convolutional Neural Networks", NIPS 2012
29/09/2012 Magnus Burénius B. Pepik, P. Gehler, M. Stark and B. Schiele. "3D^2PM - 3D Deformable Part Models", ECCV 2012
B. Pepik, M. Stark, P. Gehler and B. Schiele. "Teaching 3D Geometry to Deformable Part Models" CVPR 2012
Slides PDF
22/09/2012 Josephine Sullivan Devi Parikh, Kirsten Grauman. "Relative Attributes", ICCV 2011
and some insights on Rank SVMs
Slides PPT
04/09/2012 Amin Sadeghi, UIUC (Invited Talk) Amin Sadeghi, Ali Farhadi. "Recognition Using Visual Phrases", CVPR 2011 and recent related works...
29/08/2012 Vahid Kazemi Vahid Kazemi, Josephine Sullivan. "Using Richer Models for Articulated Pose Estimation of Footballers", BMVC 2012
24/08/2012 Miroslav Kobetski Andrea Vedaldi, Andrew Zisserman. "Sparse Kernel Approximations for Efficient Classification and Detection", CVPR 2012
17/08/2012 Vahid Kazemi Ross Girshick, et al. "Efficient Regression of General-Activity Human Poses from Depth Images", ICCV 2011
Jamie Shotton, et al. "Real-Time Human Pose Recognition in Parts from a Single Depth Image", CVPR 2011
10/08/2012 Hossein Azizpour B. Hariharan, J. Malik, and D. Ramanan. Discriminative Decorrelation for Clustering and Classification. ECCV 2012 Slides PPT
Slides PDF
29/06/2012 Josephine Sullivan Quoc Le, et al. Building high-level features using large scale unsupervised learning. ICML 2012
Overview of Deep Learning
15/06/2012 Miroslav Kobetski A. Bergamo L. Torresani, Exploiting weakly-labeled Web images to improve object classification: a domain adaptation approach. NIPS 2012
08/06/2012 Heydar Maboudi Joint Feature Clustering and Classification
25/05/2012 Magnus Burénius B. Sapp, D. Weiss, B. Taskar "Parsing human motion with stretchable models" CVPR 2011 Slides PDF
04/05/2012 Omid Aghazadeh H. Pirsiavash, D. Ramanan "Steerable Part Models" CVPR 2012
26/04/2012 Hossein Azizpour H. Pirsiavash, D. Ramanan "Detecting Activities of Daily Living in First-person Camera Views" CVPR 2012 Slides PPT
Slides PDF
09/02/2012 Bernt Schiele, MPI (Invited Talk) "3D Scene Understanding - It's Time to Address it Again"
03/02/2012 Josephine Sullivan M. Belkin, P. Niyogi, V. Sindhwani. "Manifold Regularization: a Geometric Framework for Learning from Labeled and Unlabeled Examples" JMLR 2006
Chapter 5 of "Introduction to Semi-Supervised Learning"
Text Book
27/01/2012 Heydar Maboudi Nobuyuki Morioka, "Building Compact Local Pairwise Codebook with joint feature space clustering" ECCV 2010
20/01/2012 Miroslav Kobetski M. Enzweiler and D. M. Gavrila. "A Mixed Generative-Discriminative Framework for Pedestrian Classification." CVPR 2008
21/12/2011 Ivan Laptev, INRIA/WILLOW (Invited Talk) "Human action recognition: The challenges and recent progress"
15/12/2011 Omid Aghazadeh Liu, Yuen and Torralba, SIFT Flow: Dense Correspondence across Scenes and its Applications, 2011, PAMI
Duchenne, Joulin and Ponce, A Graph-Matching Kernel for Object Categorization, 2011, ICCV
Tighe and Lazebnik, SuperParsing: Scalable Nonparametric Image Parsing with Superpixels, 2010, ECCV
Liu, Yuen and Torralba, Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment, 2009, CVPR
Li, Socher and Fei-Fei, Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework, 2009, CVPR
09/12/2011 Hossein Azizpour T. Malisiewicz, A. Gupta, and A. A. Efros "Ensemble of Exemplar-SVMs for Object Detection and Beyond" ICCV 2011 Slides
02/12/2011 Magnus Burenius R. Farrell, O. Oza, N. Zhang, V. I. Morariu, T. Darrell, L. S. Davis. "Birdlets: Subordinate Categorization Using Volumetric Primitives and Pose-Normalized Appearance." ICCV 2011 Slides
21/10/2011 Josephine Sullivan V. A. Prisacariu, I. Reid "Nonlinear Shape Manifolds as Shape Priors in Level Set Segmentation and Tracking" CVPR 2011 Slides
14/10/2011 Omid Aghazadeh Brown, Hua and Winder, Discriminative Learning of Local Image Descriptors, 2011, PAMI
Rublee, Rabaud, Konolige and Bradski, ORB: an efficient alternative to SIFT or SURF, 2011, ICCV
Leutenegger,Chli and Siegwart, BRISK: Binary Robust Invariant Scalable Keypoints, 2011, ICCV
Tuytelaars, Dense Interest Points, 2010, CVPR
Calonder, Lepetit, Strecha and Fua, BRIEF: Binary Robust Independent Elementary Features, 2010, ECCV
Mikolajczyk and Schmid, A Performance Evaluation of Local Descriptors, 2005, PAMI
07/10/2011 Omid Aghazadeh Mikolajczyk and Schmid, Scale & Affine Invariant Interest Point Detectors, 2004, IJCV
Mikolajczyk and Schmid, A Performance Evaluation of Local Descriptors, 2005, PAMI
Mikolajczyk, Tuytelaars, Schmid, Zisserman, Matas, Schaffalitzky, Kadir and Van Gool, A Comparison of Affine Region Detectors, 2006, IJCV
Winder and Brown, Learning Local Image Descriptors, 2007, CVPR
30/09/2011 Miroslav Kobetski M. Pedersoli, A. Vedaldi, J. Gonzalez "A coarse-to-fine approach for fast deformable object detection" CVPR 2011
23/09/2011 Hossein Azizpour Branson S., Perona P., Belongie S., "Strong Supervision From Weak Annotation: Interactive Training of Deformable Part Models", ICCV 2011 Slides PPT
Slides PDF
09/09/2011 Heydar Maboudi Parag, T.; Elgammal, A.; "Supervised Hypergraph Labeling" CVPR 2011
02/09/2011 Oscar Danielsson 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 a Single Depth Image" CVPR 2011 Slides
05/08/2011 Vahid Kazemi V. Kazemi and J. Sullivan "Face Alignment with Part Based Modeling" BMVC 2011 Final Paper
22/07/2011 Hossein Azizpour Deformable Parts Model and recent works around it
P. Ott and M. Everingham. "Shared parts for deformable part-based models". CVPR 2011
05/07/2011 Vahid Kazemi Y. Yang, D. Ramanan. "Articulated Pose Estimation using Flexible Mixtures of Parts" CVPR 2011 Report

Upcoming sessions calendar

Related Links

----- If you have questions, please contact azizpour${at}