H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 90 Citations 76,567 216 World Ranking 260 National Ranking 14

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Computer vision
  • Machine learning

His primary areas of study are Artificial intelligence, Computer vision, Pattern recognition, Optical flow and Convolutional neural network. His studies link Machine learning with Artificial intelligence. Thomas Brox works mostly in the field of Computer vision, limiting it down to concerns involving Point and, occasionally, Conjugate gradient method, Match moving and Tracking.

The Pattern recognition study combines topics in areas such as Annotation and Data set. His study looks at the relationship between Segmentation and topics such as Image processing, which overlap with Usability. His work deals with themes such as Pose, Brain segmentation and Image translation, which intersect with Deep learning.

His most cited work include:

  • U-Net: Convolutional Networks for Biomedical Image Segmentation (20640 citations)
  • High Accuracy Optical Flow Estimation Based on a Theory for Warping (2068 citations)
  • 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation (1644 citations)

What are the main themes of his work throughout his whole career to date?

The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Pattern recognition, Segmentation and Image segmentation. His study looks at the intersection of Artificial intelligence and topics like Machine learning with Training set. His biological study deals with issues like Artificial neural network, which deal with fields such as Representation.

The study incorporates disciplines such as Pixel, Object detection and Benchmark in addition to Segmentation. His Image segmentation study typically links adjacent topics like Image processing. His research in Optical flow intersects with topics in Matching, Flow, Frame rate and Image warping.

He most often published in these fields:

  • Artificial intelligence (77.95%)
  • Computer vision (45.65%)
  • Pattern recognition (26.09%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (77.95%)
  • Computer vision (45.65%)
  • Segmentation (21.43%)

In recent papers he was focusing on the following fields of study:

His primary areas of investigation include Artificial intelligence, Computer vision, Segmentation, Network architecture and Pattern recognition. His research investigates the link between Artificial intelligence and topics such as Machine learning that cross with problems in Representation. His work on RGB color model, Visual servoing and Tracking as part of general Computer vision research is frequently linked to Motor cortex and Spontaneous movements, thereby connecting diverse disciplines of science.

He combines subjects such as Function and Weight function with his study of Segmentation. His Network architecture study combines topics from a wide range of disciplines, such as Distributed computing and Data mining. His studies in Pattern recognition integrate themes in fields like Contextual image classification and Topology.

Between 2019 and 2021, his most popular works were:

  • Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering (92 citations)
  • Understanding and Robustifying Differentiable Architecture Search (86 citations)
  • Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency (40 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Computer vision
  • Machine learning

His primary scientific interests are in Artificial intelligence, Computer vision, Contextual image classification, Feature learning and RGB color model. His work in the fields of Semi-supervised learning, Image segmentation and Deep learning overlaps with other areas such as Space. His Deep learning research includes elements of Regularization, Curvature, Relaxation, Generalization and Convolutional neural network.

His Computer vision research incorporates themes from Optogenetics and Premovement neuronal activity. His RGB color model study integrates concerns from other disciplines, such as Depth map, Tracking, Prior probability and Pattern recognition. He interconnects Video tracking and Benchmark in the investigation of issues within Segmentation.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Top Publications

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger;Philipp Fischer;Thomas Brox.
medical image computing and computer assisted intervention (2015)

17523 Citations

High Accuracy Optical Flow Estimation Based on a Theory for Warping

Thomas Brox;Andr ´ es Bruhn;Nils Papenberg;Joachim Weickert.
european conference on computer vision (2004)

2931 Citations

FlowNet: Learning Optical Flow with Convolutional Networks

Alexey Dosovitskiy;Philipp Fischery;Eddy Ilg;Philip Hausser.
international conference on computer vision (2015)

1508 Citations

Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

T Brox;J Malik.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2011)

1393 Citations

Striving for Simplicity: The All Convolutional Net

Jost Tobias Springenberg;Alexey Dosovitskiy;Thomas Brox;Martin A. Riedmiller.
arXiv: Learning (2014)

1331 Citations

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

Özgün Çiçek;Ahmed Abdulkadir;Ahmed Abdulkadir;Soeren S. Lienkamp;Thomas Brox.
medical image computing and computer assisted intervention (2016)

1321 Citations

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Eddy Ilg;Nikolaus Mayer;Tonmoy Saikia;Margret Keuper.
computer vision and pattern recognition (2017)

1196 Citations

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Nikolaus Mayer;Eddy Ilg;Philip Hausser;Philipp Fischer.
computer vision and pattern recognition (2016)

960 Citations

Object segmentation by long term analysis of point trajectories

Thomas Brox;Jitendra Malik.
european conference on computer vision (2010)

811 Citations

FlowNet: Learning Optical Flow with Convolutional Networks

Philipp Fischer;Alexey Dosovitskiy;Eddy Ilg;Philip Häusser.
arXiv: Computer Vision and Pattern Recognition (2015)

654 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Top Scientists Citing Thomas Brox

Dinggang Shen

Dinggang Shen

ShanghaiTech University

Publications: 127

Daniel Cremers

Daniel Cremers

Technical University of Munich

Publications: 112

Nassir Navab

Nassir Navab

Technical University of Munich

Publications: 106

Alan L. Yuille

Alan L. Yuille

Johns Hopkins University

Publications: 100

Luc Van Gool

Luc Van Gool

ETH Zurich

Publications: 100

Joachim Weickert

Joachim Weickert

Saarland University

Publications: 97

Pheng-Ann Heng

Pheng-Ann Heng

Chinese University of Hong Kong

Publications: 89

Daniel Rueckert

Daniel Rueckert

Technical University of Munich

Publications: 82

Ming-Hsuan Yang

Ming-Hsuan Yang

University of California, Merced

Publications: 79

Jitendra Malik

Jitendra Malik

University of California, Berkeley

Publications: 77

Stefano Soatto

Stefano Soatto

University of California, Los Angeles

Publications: 76

Andreas Maier

Andreas Maier

University of Erlangen-Nuremberg

Publications: 71

Christian Theobalt

Christian Theobalt

Max Planck Institute for Informatics

Publications: 70

Thomas Pock

Thomas Pock

Graz University of Technology

Publications: 65

Marc Pollefeys

Marc Pollefeys

ETH Zurich

Publications: 64

Something went wrong. Please try again later.