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.
A unified architecture for natural language processing
20083.2k citationsRonan Collobert, Jason Westonprofile →
Curriculum learning
20092.6k citationsRonan Collobert, Jason Weston et al.profile →
Countries citing papers authored by Ronan Collobert
Since
Specialization
Citations
This map shows the geographic impact of Ronan Collobert'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 Ronan Collobert with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ronan Collobert more than expected).
This network shows the impact of papers produced by Ronan Collobert. 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 Ronan Collobert. The network helps show where Ronan Collobert may publish in the future.
Co-authorship network of co-authors of Ronan Collobert
This figure shows the co-authorship network connecting the top 25 collaborators of Ronan Collobert.
A scholar is included among the top collaborators of Ronan Collobert 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 Ronan Collobert. Ronan Collobert is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Pratap, Vineel, Qiantong Xu, Tatiana Likhomanenko, Gabriel Synnaeve, & Ronan Collobert. (2022). Word Order does not Matter for Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 7202–7206.3 indexed citations
Palaz, Dimitri, Mathew Magimai.-Doss, & Ronan Collobert. (2015). Learning linearly separable features for speech recognition using convolutional neural networks. Infoscience (Ecole Polytechnique Fédérale de Lausanne).2 indexed citations
8.
Collobert, Ronan, et al.. (2015). Learning to Segments Objects Candidates. Infoscience (Ecole Polytechnique Fédérale de Lausanne).4 indexed citations
9.
Pinheiro, Pedro O. & Ronan Collobert. (2015). From image-level to pixel-level labeling with Convolutional Networks. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 1713–1721.416 indexed citations breakdown →
10.
Collobert, Ronan, et al.. (2014). Weakly Supervised Semantic Segmentation with Convolutional Networks.. arXiv (Cornell University).25 indexed citations
Collobert, Ronan & Jason Weston. (2007). Fast Semantic Extraction Using a Novel Neural Network Architecture. Meeting of the Association for Computational Linguistics. 560–567.41 indexed citations
18.
Collobert, Ronan, Fabian H. Sinz, Jason Weston, & Léon Bottou. (2006). Trading convexity for scalability. GoeScholar The Publication Server of the Georg-August-Universität Göttingen (Georg-August-Universität Göttingen). 201–208.254 indexed citations
19.
Collobert, Ronan, Fabian H. Sinz, Jason Weston, & Léon Bottou. (2006). Large Scale Transductive SVMs. Journal of Machine Learning Research. 7(62). 1687–1712.355 indexed citations
20.
Weston, Jason, Ronan Collobert, Fabian H. Sinz, Léon Bottou, & Vladimir Vapnik. (2006). Inference with the Universum. GoeScholar The Publication Server of the Georg-August-Universität Göttingen (Georg-August-Universität Göttingen). 1009–1016.141 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.