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.
Boundary loss for highly unbalanced segmentation
2020274 citationsChristian Desrosiers, Éric Granger et al.Medical Image Analysisprofile →
Author Peers
Peers are selected by citation overlap in the author's most active subfields.
citations ·
hero ref
Countries citing papers authored by Ismail Ben Ayed
Since
Specialization
Citations
This map shows the geographic impact of Ismail Ben Ayed'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 Ismail Ben Ayed with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ismail Ben Ayed more than expected).
This network shows the impact of papers produced by Ismail Ben Ayed. 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 Ismail Ben Ayed. The network helps show where Ismail Ben Ayed may publish in the future.
Co-authorship network of co-authors of Ismail Ben Ayed
This figure shows the co-authorship network connecting the top 25 collaborators of Ismail Ben Ayed.
A scholar is included among the top collaborators of Ismail Ben Ayed 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 Ismail Ben Ayed. Ismail Ben Ayed is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Rony, Jérôme, et al.. (2020). Metric learning: cross-entropy vs. pairwise losses. arXiv (Cornell University).3 indexed citations
14.
Bhuiyan, Amran, et al.. (2020). Flow-Guided Attention Networks for Video-Based Person Re-Identification. arXiv (Cornell University).1 indexed citations
15.
Rony, Jérôme, et al.. (2020). Information Maximization for Few-Shot Learning. Neural Information Processing Systems. 33. 2445–2457.32 indexed citations
16.
Belharbi, Soufiane, Jérôme Rony, José Dolz, et al.. (2019). Weakly Supervised Object Localization using Min-Max Entropy: an Interpretable Framework.. arXiv (Cornell University).1 indexed citations
17.
Granger, Éric, et al.. (2019). Clustering with Fairness Constraints: A Flexible and Scalable Approach. arXiv (Cornell University).2 indexed citations
18.
Belharbi, Soufiane, Ismail Ben Ayed, Luke McCaffrey, & Éric Granger. (2019). Deep Ordinal Classification with Inequality Constraints.. arXiv (Cornell University).4 indexed citations
Dolz, José, Ismail Ben Ayed, Jing Yuan, & Christian Desrosiers. (2017). HyperDense-Net: A hyper-densely connected CNN for multi-modal image semantic segmentation.. arXiv (Cornell University).5 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.