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 Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression
20102.8k citationsJeffrey F. Cohn, Takeo Kanade et al.profile →
Neural network-based face detection
19982.4k citationsTakeo Kanade et al.IEEE Transactions on Pattern Analysis and Machine Intelligenceprofile →
Shape and motion from image streams under orthography: a factorization method
This map shows the geographic impact of Takeo Kanade'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 Takeo Kanade with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Takeo Kanade more than expected).
This network shows the impact of papers produced by Takeo Kanade. 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 Takeo Kanade. The network helps show where Takeo Kanade may publish in the future.
Co-authorship network of co-authors of Takeo Kanade
This figure shows the co-authorship network connecting the top 25 collaborators of Takeo Kanade.
A scholar is included among the top collaborators of Takeo Kanade 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 Takeo Kanade. Takeo Kanade is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Joo, Hanbyul, Hao Liu, Lei Tan, et al.. (2015). Panoptic Studio: A Massively Multiview System for Social Motion Capture. 3334–3342.306 indexed citations breakdown →
4.
Gross, Ralph, Iain Matthews, Jeffrey P. Cohn, Takeo Kanade, & Simon Baker. (2008). Multi-PIE. 1–8.265 indexed citations
Faugeras, Olivier, et al.. (1998). Geometric motion segmentation and model selection - Discussion. Cambridge University Engineering Department Publications Database.2 indexed citations
Kanade, Takeo, et al.. (1993). A paraperspective factorization method for shape and motion recovery. Defense Technical Information Center (DTIC). 94. 31929.17 indexed citations
14.
Kanade, Takeo, et al.. (1991). A VLSI sensor based rangefinding system. International Symposium on Robotics. 49–56.19 indexed citations
15.
Kanade, Takeo & Katsushi Ikeuchi. (1991). Introduction to the Special Issue on Physical Modeling in Computer Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 13(7). 609–610.6 indexed citations
16.
Ohta, Yuichi & Takeo Kanade. (1985). Stereo by two-level dynamic programming. International Joint Conference on Artificial Intelligence. 1120–1126.21 indexed citations
17.
Wallace, R.S., et al.. (1985). First results in robot road-following. International Joint Conference on Artificial Intelligence. 1089–1095.133 indexed citations
18.
Herman, Martin, et al.. (1983). The 3D MOSAIC Scene Understanding System.. International Joint Conference on Artificial Intelligence. 1108–1112.11 indexed citations
19.
Ohta, Yuichi, Takeo Kanade, & Toshiyuki Sakai. (1979). A production system for region analysis. International Joint Conference on Artificial Intelligence. 684–686.7 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.