Search Results for author: Ondřej Chum

Found 14 papers, 10 papers with code

Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations

1 code implementation4 Nov 2019 James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum

This paper introduces minimal solvers that jointly solve for radial lens undistortion and affine-rectification using local features extracted from the image of coplanar translated and reflected scene texture, which is common in man-made environments.

Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower

1 code implementation ICCV 2019 Giorgos Tolias, Filip Radenovic, Ondřej Chum

We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction.

Adversarial Attack

No Fear of the Dark: Image Retrieval under Varying Illumination Conditions

no code implementations ICCV 2019 Tomas Jenicek, Ondřej Chum

Image retrieval under varying illumination conditions, such as day and night images, is addressed by image preprocessing, both hand-crafted and learned.

Image Retrieval

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales

1 code implementation25 Jul 2019 James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum

The proposed solvers use the affine invariant that coplanar repeats have the same scale in rectified space.

Linking Art through Human Poses

no code implementations8 Jul 2019 Tomas Jenicek, Ondřej Chum

We address the discovery of composition transfer in artworks based on their visual content.

Content-Based Image Retrieval

Understanding and Improving Kernel Local Descriptors

3 code implementations27 Nov 2018 Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

2 code implementations CVPR 2018 Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum

In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.

Image Retrieval

Fine-tuning CNN Image Retrieval with No Human Annotation

13 code implementations3 Nov 2017 Filip Radenović, Giorgos Tolias, Ondřej Chum

We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.

Image Retrieval

Asymmetric Feature Maps with Application to Sketch Based Retrieval

no code implementations CVPR 2017 Giorgos Tolias, Ondřej Chum

To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval.

Sketch-Based Image Retrieval Translation

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

5 code implementations8 Apr 2016 Filip Radenović, Giorgos Tolias, Ondřej Chum

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.

Image Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.