Search Results for author: Jiří Matas

Found 22 papers, 11 papers with code

Discriminative Correlation Filter with Channel and Spatial Reliability

4 code implementations CVPR 2017 Alan Lukežič, Tomáš Vojíř, Luka Čehovin, Jiří Matas, Matej Kristan

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance.

Ranked #13 on Visual Object Tracking on VOT2017/18 (using extra training data)

Visual Object Tracking

Depth Masked Discriminative Correlation Filter

no code implementations26 Feb 2018 Uğur Kart, Joni-Kristian Kämäräinen, Jiří Matas, Lixin Fan, Francesco Cricri

Depth information provides a strong cue for occlusion detection and handling, but has been largely omitted in generic object tracking until recently due to lack of suitable benchmark datasets and applications.

Object Tracking

Now you see me: evaluating performance in long-term visual tracking

no code implementations19 Apr 2018 Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan

We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances.

Benchmarking Visual Tracking

Continual Occlusions and Optical Flow Estimation

no code implementations5 Nov 2018 Michal Neoral, Jan Šochman, Jiří Matas

We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25\% on both KITTI and Sintel.

Occlusion Estimation Optical Flow Estimation

Leveraging Outdoor Webcams for Local Descriptor Learning

1 code implementation28 Jan 2019 Milan Pultar, Dmytro Mishkin, Jiří Matas

We present AMOS Patches, a large set of image cut-outs, intended primarily for the robustification of trainable local feature descriptors to illumination and appearance changes.

Clustering

Intra-frame Object Tracking by Deblatting

3 code implementations9 May 2019 Jan Kotera, Denys Rozumnyi, Filip Šroubek, Jiří Matas

We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object.

Deblurring Image Matting +3

Visual Coin-Tracking: Tracking of Planar Double-Sided Objects

no code implementations7 Aug 2019 Jonáš Šerých, Jiří Matas

We introduce a new video analysis problem -- tracking of rigid planar objects in sequences where both their sides are visible.

Segmentation Semantic Segmentation

Non-Causal Tracking by Deblatting

2 code implementations15 Sep 2019 Denys Rozumnyi, Jan Kotera, Filip Šroubek, Jiří Matas

Tracking by Deblatting stands for solving an inverse problem of deblurring and image matting for tracking motion-blurred objects.

Deblurring Image Matting

D3S -- A Discriminative Single Shot Segmentation Tracker

1 code implementation20 Nov 2019 Alan Lukežič, Jiří Matas, Matej Kristan

D3S outperforms the leading segmentation tracker SiamMask on video object segmentation benchmark and performs on par with top video object segmentation algorithms, while running an order of magnitude faster, close to real-time.

Object Segmentation +4

Danish Fungi 2020 -- Not Just Another Image Recognition Dataset

1 code implementation18 Mar 2021 Lukáš Picek, Milan Šulc, Jiří Matas, Jacob Heilmann-Clausen, Thomas S. Jeppesen, Thomas Læssøe, Tobias Frøslev

Interestingly, ViT achieves results superior to CNN baselines with 80. 45% accuracy and 0. 743 macro F1 score, reducing the CNN error by 9% and 12% respectively.

Classifier calibration Fine-Grained Image Classification +2

A Discriminative Single-Shot Segmentation Network for Visual Object Tracking

no code implementations22 Dec 2021 Alan Lukežič, Jiří Matas, Matej Kristan

D3S2 outperforms the leading segmentation tracker SiamMask on video object segmentation benchmarks and performs on par with top video object segmentation algorithms.

Object Segmentation +4

Matching with AffNet based rectifications

no code implementations29 Jul 2022 Václav Vávra, Dmytro Mishkin, Jiří Matas

We consider the problem of two-view matching under significant viewpoint changes with view synthesis.

DocILE Benchmark for Document Information Localization and Extraction

1 code implementation11 Feb 2023 Štěpán Šimsa, Milan Šulc, Michal Uřičář, Yash Patel, Ahmed Hamdi, Matěj Kocián, Matyáš Skalický, Jiří Matas, Antoine Doucet, Mickaël Coustaty, Dimosthenis Karatzas

This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition.

Key Information Extraction Unsupervised Pre-training

MFT: Long-Term Tracking of Every Pixel

1 code implementation22 May 2023 Michal Neoral, Jonáš Šerých, Jiří Matas

We propose MFT -- Multi-Flow dense Tracker -- a novel method for dense, pixel-level, long-term tracking.

Point Tracking

Improving 2D Human Pose Estimation across Unseen Camera Views with Synthetic Data

1 code implementation13 Jul 2023 Miroslav Purkrábek, Jiří Matas

Human Pose Estimation is a thoroughly researched problem; however, most datasets focus on the side and front-view scenarios.

2D Human Pose Estimation Pose Estimation +1

Dense Matchers for Dense Tracking

no code implementations17 Feb 2024 Tomáš Jelínek, Jonáš Šerých, Jiří Matas

Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion.

3D Reconstruction Optical Flow Estimation +2

EE3P: Event-based Estimation of Periodic Phenomena Properties

1 code implementation22 Feb 2024 Jakub Kolář, Radim Špetlík, Jiří Matas

We introduce a novel method for measuring properties of periodic phenomena with an event camera, a device asynchronously reporting brightness changes at independently operating pixels.

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