Lecture notes in computer science (3 papers)arXiv (Cornell University) (1 paper)IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (3 papers)IEEE/CVF International Conference on Computer Vision (ICCV) (1 paper)
Paper score: A paper's citations measured against the top-1% bar of its own field and year: the square root of citations ÷ bar, so 1 means right at the bar and 2 means four times its citations. The bar blends the citation counts that enter the top 1% of the paper's subfields in its year (weighted 89.5%), of those subfields over all years (0.5%) and of its year across all fields (10%); a subfield and year with fewer than 400 papers takes its year's bar. Papers from 2026 are not scored yet: in an unfinished year, when a paper appeared matters more than how it is cited.
Hit paper: A paper cited at least 1.5× the top-1% bar of its field and year: a paper score of at least √1.5.
2019IEEE/CVF International Conference on Computer Vision (ICCV)
2019IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
2018IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
This map shows the geographic impact of Mark Sandler'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 Mark Sandler with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Mark Sandler more than expected).
This network shows the impact of papers produced by Mark Sandler. 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 Mark Sandler. The network helps show where Mark Sandler may publish in the future.
Co-authors
The 25 scholars most cited alongside Mark Sandler, linked wherever they
have co-authored with each other. Click a name or a connecting line to browse the papers
they share.
Border = papers with Mark SandlerLine = papers co-authored togetherMark Sandler links everyone, so they are left out of the graph.
All Works
8 of 8 papers shown
#
Work
1
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Nuclear Energy and Engineering, Waste Management and Disposal and Infectious Diseases, having authored 8 papers that have together received 28.4k indexed citations. Recurring topics across this work include Advanced Neural Network Applications (8 papers) and Domain Adaptation and Few-Shot Learning (1 paper). The work is most often cited by research in Computer Vision and Pattern Recognition (15.6k citations), Artificial Intelligence (4k citations), Hardware and Architecture (876 citations), Media Technology (964 citations) and Industrial and Manufacturing Engineering (1k citations). Mark Sandler has collaborated with scholars based in United States. Frequent co-authors include Andrew Howard, Liang-Chieh Chen, Andrey Zhmoginov, Menglong Zhu, Vijay Vasudevan, Ruoming Pang, Quoc Viet Le, Mingxing Tan, Hartwig Adam and Weijun Wang. Their work appears in journals such as Lecture notes in computer science, arXiv (Cornell University), IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings and IEEE/CVF International Conference on Computer Vision (ICCV).
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.