Maxim Berman

1.5k total citations · 2 hit papers
6 papers, 847 citations indexed

About

Maxim Berman is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Computational Mechanics. According to data from OpenAlex, Maxim Berman has authored 6 papers receiving a total of 847 indexed citations (citations by other indexed papers that have themselves been cited), including 4 papers in Computer Vision and Pattern Recognition, 4 papers in Artificial Intelligence and 1 paper in Computational Mechanics. Recurrent topics in Maxim Berman's work include Advanced Neural Network Applications (4 papers), Machine Learning and Algorithms (3 papers) and Stochastic Gradient Optimization Techniques (2 papers). Maxim Berman is often cited by papers focused on Advanced Neural Network Applications (4 papers), Machine Learning and Algorithms (3 papers) and Stochastic Gradient Optimization Techniques (2 papers). Maxim Berman collaborates with scholars based in Belgium and Austria. Maxim Berman's co-authors include Matthew B. Blaschko, Amal Rannen Triki, Frederik Maes, Raf Bisschops, Dirk Vandermeulen, Jeroen Bertels, Tom Eelbode, Christos Sagonas and Vladimir Kolmogorov and has published in prestigious journals such as IEEE Transactions on Medical Imaging, arXiv (Cornell University) and Lirias (KU Leuven).

In The Last Decade

Maxim Berman

6 papers receiving 819 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks

2018 570 citations Maxim Berman, Amal Rannen Triki et al. Lirias (KU Leuven) profile →
Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index

2020 250 citations Tom Eelbode, Jeroen Bertels et al. IEEE Transactions on Medical Imaging profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Maxim Berman Belgium	4	425	172	152	112	88	6	847
Amal Rannen Triki Belgium	3	332 0.8×	110 0.6×	61 0.4×	106 0.9×	75 0.9×	4	602
Lihe Yang China	7	570 1.3×	281 1.6×	89 0.6×	50 0.4×	169 1.9×	10	931
Wei Xiong Singapore	15	426 1.0×	150 0.9×	168 1.1×	30 0.3×	77 0.9×	94	911
Xiaokang Chen China	11	846 2.0×	408 2.4×	184 1.2×	50 0.4×	152 1.7×	38	1.2k
Marie-Pierre Dubuisson United States	7	687 1.6×	165 1.0×	140 0.9×	45 0.4×	91 1.0×	10	1.2k
David Acuna Canada	7	603 1.4×	207 1.2×	81 0.5×	99 0.9×	126 1.4×	13	867
Zhenghao Shi China	13	296 0.7×	139 0.8×	166 1.1×	59 0.5×	176 2.0×	69	695
Panqu Wang United States	3	895 2.1×	299 1.7×	149 1.0×	83 0.7×	280 3.2×	6	1.4k
Nahian Siddique United States	8	431 1.0×	270 1.6×	326 2.1×	127 1.1×	91 1.0×	12	1.3k

Countries citing papers authored by Maxim Berman

Since Specialization

Citations

This map shows the geographic impact of Maxim Berman's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Maxim Berman with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Maxim Berman more than expected).

Fields of papers citing papers by Maxim Berman

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Maxim Berman. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Maxim Berman. The network helps show where Maxim Berman may publish in the future.

Co-authorship network of co-authors of Maxim Berman

This figure shows the co-authorship network connecting the top 25 collaborators of Maxim Berman. A scholar is included among the top collaborators of Maxim Berman based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Maxim Berman. Maxim Berman is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

6 of 6 papers shown

1.

Eelbode, Tom, Jeroen Bertels, Maxim Berman, et al.. (2020). Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index. IEEE Transactions on Medical Imaging. 39(11). 3679–3690. 250 indexed citations breakdown →

2.

Berman, Maxim, et al.. (2019). Function Norms for Neural Networks. Lirias (KU Leuven). 70. 748–752. 1 indexed citations

3.

Triki, Amal Rannen, et al.. (2019). A Bayesian Optimization Framework for Neural Network Compression. Lirias (KU Leuven). 10273–10282. 16 indexed citations

4.

Berman, Maxim, Amal Rannen Triki, & Matthew B. Blaschko. (2018). The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks. Lirias (KU Leuven). 4413–4421. 570 indexed citations breakdown →

5.

Triki, Amal Rannen, Maxim Berman, & Matthew B. Blaschko. (2017). Stochastic Weighted Function Norm Regularization.. arXiv (Cornell University). 1 indexed citations

6.

Berman, Maxim & Matthew B. Blaschko. (2017). Optimization of the Jaccard index for image segmentation with the Lovász hinge.. arXiv (Cornell University). 9 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact