Papers discussed at Computer Vision Track, Winter School 2017, Computer Science @ UCU

awesome-lvcs-cv.md

The course: https://cw.fel.cvut.cz/wiki/courses/ucuws17/start

BoW

• Video Google: A Text Retrieval Approach to Object Matching in Videos http://www.robots.ox.ac.uk/~vgg/publications/papers/sivic03.pdf

• CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples https://arxiv.org/abs/1604.02426

Local Features

• A COMBINED CORNER AND EDGE DETECTOR https://www.cis.rit.edu/~cnspci/references/dip/feature_extraction/harris1988.pdf

• SIFT http://www.cs.ubc.ca/~lowe/keypoints/

• LIFT https://arxiv.org/abs/1603.09114

• Hessian Affine http://www.robots.ox.ac.uk/~vgg/research/affine/

• Efficient Image Detail Mining http://cmp.felk.cvut.cz/~chum/papers/mikulik_accv14.pdf

• Recognising Panoramas http://www.cs.ubc.ca/~lowe/papers/brown03.pdf

• Scale Space Theory https://www.kth.se/profile/tony/page/scale-space-theory

• impHarris http://waset.org/publications/11793/feature-point-detection-by-combining-advantages-of-intensity-based-approach-and-edge-based-approach

• Indexing based on scale invariant interest points https://hal.inria.fr/inria-00548276/document/ (Harris Laplacian) — tldr Harris instead of DoG in DoG-DoG

• Matching Widely Separated Views Based on Affine Invariant Regions https://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/tuytelaars_ijcv2004.pdf

• MSER https://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/matas_bmvc2002.pdf

• MODS: Fast and Robust Method for Two-View Matching https://arxiv.org/abs/1503.02619

• Histograms of Oriented Gradients for Human Detection https://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf

• Measuring the objectness of image windows https://www.vision.ee.ethz.ch/publications/papers/techreports/eth_biwi_00882.pdf http://groups.inf.ed.ac.uk/calvin/objectness/

Geometry

• Hartley & Zisserman http://www.robots.ox.ac.uk/~vgg/hzbook/

• Tomas Pajdla's Geometry course http://cmp.felk.cvut.cz/~pajdla/

Model Fitting

• RANSAC http://www.cs.columbia.edu/~belhumeur/courses/compPhoto/ransac.pdf

• Differentiable RANSAC https://arxiv.org/abs/1611.05705

• PROSAC http://cmp.felk.cvut.cz/~matas/papers/chum-prosac-cvpr05.pdf

Retrieval

• THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE (Jaccard) https://dx.doi.org/10.1111%2Fj.1469-8137.1912.tb05611.x

• Near Duplicate Image Detection: min-Hash and tf-idf Weighting https://www.robots.ox.ac.uk/~vgg/publications/papers/chum08a.pdf

• Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval http://www.robots.ox.ac.uk/~vgg/publications/papers/chum07b.pdf

• Total Recall II: Query Expansion Revisited http://cmp.felk.cvut.cz/~chum/papers/chum_cvpr11.pdf

• K-means++ http://ilpubs.stanford.edu:8090/778/1/2006-13.pdf

• FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION http://www.cs.ubc.ca/research/flann/uploads/FLANN/flann_visapp09.pdf

• J-linkage http://www.diegm.uniud.it/fusiello/demo/jlk/

• Randomized Trees for Real-Time Keypoint Recognition http://cvlabwww.epfl.ch/~lepetit/ http://cvlabwww.epfl.ch/~lepetit/papers/lepetit_cvpr05.pdf

• Fast Keypoint Recognition using Random Ferns http://cvlabwww.epfl.ch/~lepetit/papers/ozuysal_pami10.pdf

Tracking

• Good Features To Track http://www.inf.fu-berlin.de/lehre/SS06/SeminarComputerVision/origReport_von_Carlo_Tomasi.pdf

• The World of Fast Moving Objects https://arxiv.org/abs/1611.07889

• Detection and Tracking of Point Features https://cecas.clemson.edu/~stb/klt/tomasi-kanade-techreport-1991.pdf

• An iterative image registration technique with an application to stereo vision https://cecas.clemson.edu/~stb/klt/lucas_bruce_d_1981_1.pdf

• Determining Optical Flow http://image.diku.dk/imagecanon/material/HornSchunckOptical_Flow.pdf

• SIFT Flow: Dense Correspondence across Different Scenes http://people.csail.mit.edu/celiu/ECCV2008/SIFTflow.pdf

• EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow https://arxiv.org/abs/1501.02565

• FlowNet: Learning Optical Flow with Convolutional Networks https://arxiv.org/abs/1504.06852

• FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks https://arxiv.org/abs/1612.01925

• A Naturalistic Open Source Movie for Optical Flow Evaluation http://files.is.tue.mpg.de/black/papers/ButlerECCV2012.pdf

• Forward-Backward Error: Automatic Detection of Tracking Failures http://personal.ee.surrey.ac.uk/Personal/Z.Kalal/Publications/2010_icpr.pdf

• Robustifying the Flock of Trackers http://cmp.felk.cvut.cz/~vojirtom/publications/cvww2011.pdf http://cmp.felk.cvut.cz/~vojirtom/asw/FoT/

• You Only Look Once: Unified, Real-Time Object Detection https://arxiv.org/abs/1506.02640

CNN

• Deep Residual Learning for Image Recognition https://arxiv.org/abs/1512.03385

• ImageNet Classification with Deep Convolutional Neural Networks http://www.cs.toronto.edu/~kriz/

• Caffe: Convolutional Architecture for Fast Feature Embedding https://arxiv.org/abs/1408.5093

• A Taxonomy of Deep Convolutional Neural Nets for Computer Vision https://arxiv.org/abs/1601.06615

• Systematic evaluation of CNN advances on the ImageNet https://arxiv.org/abs/1606.02228

• Going Deeper with Convolutions https://arxiv.org/abs/1409.4842

• Deep Networks with Stochastic Depth https://arxiv.org/abs/1603.09382

• Very Deep Convolutional Networks for Large-Scale Image Recognition https://arxiv.org/abs/1409.1556

• Identity Mappings in Deep Residual Networks https://arxiv.org/abs/1603.05027

• Xception: Deep Learning with Depthwise Separable Convolutions https://arxiv.org/abs/1610.02357

• Learning Multiple Layers of Features from Tiny Images http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf (kriz' MSc thesis)

• All you need is a good init https://arxiv.org/abs/1511.06422

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift https://arxiv.org/abs/1502.03167

• Empirical Evaluation of Rectified Activations in Convolutional Network https://arxiv.org/abs/1505.00853

• A guide to convolution arithmetic for deep learning https://arxiv.org/abs/1603.07285

• Object Detection Networks on Convolutional Feature Maps https://arxiv.org/abs/1504.06066

• Convolutional Neural Networks at Constrained Time Cost https://arxiv.org/abs/1412.1710

• Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion http://www.jmlr.org/papers/volume11/vincent10a/vincent10a.pdf

CNN Tracking

• Learning Multi-Domain Convolutional Neural Networks for Visual Tracking https://arxiv.org/abs/1510.07945

• Modeling and Propagating CNNs in a Tree Structure for Visual Tracking https://arxiv.org/abs/1608.07242

• Fully-Convolutional Siamese Networks for Object Tracking https://arxiv.org/abs/1606.09549

• Learning to Track at 100 FPS with Deep Regression Networks http://davheld.github.io/GOTURN/GOTURN.html

More Tracking

• Long-Term Correlation Tracking https://sites.google.com/site/chaoma99/cvpr15_tracking http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Ma_Long-Term_Correlation_Tracking_2015_CVPR_paper.pdf

• MUlti-Store Tracker (MUSTer): a Cognitive Psychology Inspired Approach to Object Tracking http://www.zbhong.com/Projects/muster

Correlation Filter Tracking

• Minimum average correlation energy filters (MACE) https://www.researchgate.net/publication/44618448_Minimum_average_correlation_energy_filters

• Visual Object Tracking using Adaptive Correlation Filters (MOSSE) http://www.cs.colostate.edu/~draper/papers/bolme_cvpr10.pdf

• Exploiting the Circulant Structure of Tracking-by-detection with Kernels (CSK) http://www.robots.ox.ac.uk/~joao/publications/henriques_eccv2012.pdf

• High-Speed Tracking with Kernelized Correlation Filters (KCF) https://arxiv.org/abs/1404.7584

• Discriminative Scale Space Tracking (DSST) https://arxiv.org/abs/1609.06141

• A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration (SAMF) http://ihpdep.github.io/ https://github.com/ihpdep/ihpdep.github.io/raw/master/papers/eccvw14_samf.pdf

• Convolutional Features for Correlation Filter Based Visual Tracking http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w14/papers/Danelljan_Convolutional_Features_for_ICCV_2015_paper.pdf

• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking http://www.cvl.isy.liu.se/research/objrec/visualtracking/conttrack/index.html

• Discriminative Correlation Filter with Channel and Spatial Reliability https://arxiv.org/abs/1611.08461

• Struck: Structured Output Tracking with Kernels http://www.samhare.net/research/files/iccv2011_struck.pdf

• Real-Time Tracking via On-line Boosting http://www.vision.ee.ethz.ch/~hegrabne/papers/Grabner2006Real-TimeTrackingvia.pdf

• Robust Object Tracking with Online Multiple Instance Learning http://vision.ucsd.edu/~bbabenko/data/miltrack-pami-final.pdf

• Tracking-Learning-Detection (TLD) http://personal.ee.surrey.ac.uk/Personal/Z.Kalal/tld.html

GAN

• NIPS 2016 Tutorial: Generative Adversarial Networks https://arxiv.org/abs/1701.00160

• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets https://arxiv.org/abs/1606.03657

• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks https://arxiv.org/abs/1701.04722

• Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space http://www.evolvingai.org/ppgn https://arxiv.org/abs/1612.00005