D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 55 Citations 22,264 356 World Ranking 2136 National Ranking 1164

Research.com Recognitions

Awards & Achievements

2016 - Fellow of the Royal Academy of Engineering (UK)

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Statistics
  • Algorithm

His primary areas of study are Artificial intelligence, Speech recognition, Pattern recognition, Algorithm and Information retrieval. The various areas that Mark Sandler examines in his Artificial intelligence study include Network architecture and Natural language processing. Mark Sandler has included themes like Time–frequency analysis, Transcription, Energy, Signal processing and Audio signal processing in his Speech recognition study.

His Algorithm research incorporates themes from Scale-invariant feature transform, Image processing, Top-hat transform, S transform and Line segment. His Information retrieval research is multidisciplinary, relying on both World Wide Web and Hierarchy. His study in Object detection is interdisciplinary in nature, drawing from both Mobile architecture, Bottleneck, Mobile device and Task.

His most cited work include:

  • MobileNetV2: Inverted Residuals and Linear Bottlenecks (3526 citations)
  • MnasNet: Platform-Aware Neural Architecture Search for Mobile (873 citations)
  • MobileNetV2: Inverted Residuals and Linear Bottlenecks (694 citations)

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

His primary scientific interests are in Artificial intelligence, Speech recognition, Algorithm, Pattern recognition and Electronic engineering. His Artificial intelligence research includes elements of Machine learning, Computer vision and Natural language processing. He works mostly in the field of Speech recognition, limiting it down to topics relating to Music information retrieval and, in certain cases, Multimedia.

Mark Sandler studies Pattern recognition, focusing on Segmentation in particular. He interconnects Pulse-width modulation, Delta-sigma modulation and Modulation in the investigation of issues within Electronic engineering. His Delta-sigma modulation research incorporates elements of Dither and Control theory.

He most often published in these fields:

  • Artificial intelligence (24.28%)
  • Speech recognition (22.46%)
  • Algorithm (11.41%)

What were the highlights of his more recent work (between 2017-2021)?

  • Artificial intelligence (24.28%)
  • Algorithm (11.41%)
  • Artificial neural network (3.80%)

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

Mark Sandler focuses on Artificial intelligence, Algorithm, Artificial neural network, Pattern recognition and Machine learning. His Natural language processing research extends to the thematically linked field of Artificial intelligence. His work in the fields of Algorithm, such as Source separation, intersects with other areas such as Visibility graph.

In the subject of general Artificial neural network, his work in Gradient descent is often linked to Mobile processor, thereby combining diverse domains of study. His research integrates issues of Segmentation, Image segmentation, Mobile device and Search algorithm in his study of Object detection. His work deals with themes such as Mobile architecture and Bottleneck, which intersect with Image segmentation.

Between 2017 and 2021, his most popular works were:

  • MobileNetV2: Inverted Residuals and Linear Bottlenecks (3526 citations)
  • MnasNet: Platform-Aware Neural Architecture Search for Mobile (873 citations)
  • MobileNetV2: Inverted Residuals and Linear Bottlenecks (694 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

His primary areas of investigation include Artificial intelligence, Artificial neural network, Algorithm, Object detection and Pattern recognition. His Artificial neural network study incorporates themes from Energy consumption, Real-time computing, Inference and Speedup. He combines subjects such as Kernel, Feature, Robust statistics, Transfer of learning and Transfer with his study of Algorithm.

His Object detection study integrates concerns from other disciplines, such as Segmentation, Image segmentation and Pyramid. Within one scientific family, Mark Sandler focuses on topics pertaining to Network architecture under Segmentation, and may sometimes address concerns connected to Next-generation network. His Image segmentation research includes themes of Mobile architecture and Bottleneck.

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.

Best Publications

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Mark Sandler;Andrew Howard;Menglong Zhu;Andrey Zhmoginov.
computer vision and pattern recognition (2018)

3860 Citations

A tutorial on onset detection in music signals

J.P. Bello;L. Daudet;S. Abdallah;C. Duxbury.
IEEE Transactions on Speech and Audio Processing (2005)

1133 Citations

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Mingxing Tan;Bo Chen;Ruoming Pang;Vijay Vasudevan.
computer vision and pattern recognition (2019)

878 Citations

Searching for MobileNetV3

Andrew Howard;Ruoming Pang;Hartwig Adam;Quoc Le.
international conference on computer vision (2019)

775 Citations

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

Andrew Howard;Andrey Zhmoginov;Liang-Chieh Chen;Mark Sandler.
(2018)

496 Citations

The Music Ontology.

Yves Raimond;Samer A. Abdallah;Mark B. Sandler;Frederick Giasson.
international symposium/conference on music information retrieval (2007)

449 Citations

Searching for MobileNetV3.

Andrew Howard;Mark Sandler;Grace Chu;Liang-Chieh Chen.
arXiv: Computer Vision and Pattern Recognition (2019)

445 Citations

Sonic visualiser: an open source application for viewing, analysing, and annotating music audio files

Chris Cannam;Christian Landone;Mark Sandler.
acm multimedia (2010)

389 Citations

Convolutional recurrent neural networks for music classification

Keunwoo Choi;Gyorgy Fazekas;Mark Sandler;Kyunghyun Cho.
international conference on acoustics, speech, and signal processing (2017)

318 Citations

Detecting harmonic change in musical audio

Christopher Harte;Mark Sandler;Martin Gasser.
Proceedings of the 1st ACM workshop on Audio and music computing multimedia (2006)

278 Citations

Best Scientists Citing Mark Sandler

Xavier Serra

Xavier Serra

Pompeu Fabra University

Publications: 64

Mark D. Plumbley

Mark D. Plumbley

University of Surrey

Publications: 62

Yi-Hsuan Yang

Yi-Hsuan Yang

Academia Sinica

Publications: 59

Meinard Müller

Meinard Müller

University of Erlangen-Nuremberg

Publications: 54

Simon Dixon

Simon Dixon

Queen Mary University of London

Publications: 48

Chunhua Shen

Chunhua Shen

University of Adelaide

Publications: 41

Joshua D. Reiss

Joshua D. Reiss

Queen Mary University of London

Publications: 39

Markus Schedl

Markus Schedl

Johannes Kepler University of Linz

Publications: 39

Gerhard Widmer

Gerhard Widmer

Johannes Kepler University of Linz

Publications: 38

Juan Pablo Bello

Juan Pablo Bello

New York University

Publications: 36

Junjie Yan

Junjie Yan

SenseTime

Publications: 36

Qi Tian

Qi Tian

Huawei Technologies (China)

Publications: 34

Song Han

Song Han

MIT

Publications: 32

Gael Richard

Gael Richard

Télécom ParisTech

Publications: 28

Masataka Goto

Masataka Goto

National Institute of Advanced Industrial Science and Technology

Publications: 28

Wenwu Wang

Wenwu Wang

University of Surrey

Publications: 27

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-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
Something went wrong. Please try again later.