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.
Graphcut textures
2003876 citationsVivek Kwatra, Arno Schödl et al.profile →
Coding, analysis, interpretation, and recognition of facial expressions
1997599 citationsIrfan Essa, Alex Pentlandprofile →
Graphcut textures
2003572 citationsVivek Kwatra, Arno Schödl et al.ACM Transactions on Graphicsprofile →
Texture optimization for example-based synthesis
2005439 citationsVivek Kwatra, Irfan Essa et al.ACM Transactions on Graphicsprofile →
Efficient hierarchical graph-based video segmentation
2010413 citationsVivek Kwatra, Irfan Essa et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Irfan Essa'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 Irfan Essa with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Irfan Essa more than expected).
This network shows the impact of papers produced by Irfan Essa. 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 Irfan Essa. The network helps show where Irfan Essa may publish in the future.
Co-authorship network of co-authors of Irfan Essa
This figure shows the co-authorship network connecting the top 25 collaborators of Irfan Essa.
A scholar is included among the top collaborators of Irfan Essa 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 Irfan Essa. Irfan Essa is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Minnen, David, Thad Starner, Irfan Essa, & Charles L. Isbell. (2007). Improving activity discovery with automatic neighborhood estimation. International Joint Conference on Artificial Intelligence. 2814–2819.34 indexed citations
6.
Hamid, Roszilah, et al.. (2005). Unsupervised activity discovery and characterization from event-streams. Uncertainty in Artificial Intelligence. 251–258.19 indexed citations
Bailón, Antonio de Haro & Irfan Essa. (2003). Exemplar-Based Surface Texture.. Vision Modeling and Visualization. 95–101.2 indexed citations
9.
Steedly, Drew, et al.. (2003). Spectral Partitioning for Structure from Motion. SMARTech Repository (Georgia Institute of Technology). 996–1003.10 indexed citations
Revéret, Lionel & Irfan Essa. (2001). Visual Coding and Tracking of Speech Related Facial Motion. HAL (Le Centre pour la Communication Scientifique Directe).12 indexed citations
Brand, Matthew & Irfan Essa. (1995). Causal Analysis for Visual Gesture Understanding.12 indexed citations
19.
Essa, Irfan & Alex Pentland. (1994). A Vision System for Observing and Extracting Facial Action Parameters. Computer Vision and Pattern Recognition. 76–83.94 indexed citations
20.
Essa, Irfan, Stan Sclaroff, & Alex Pentland. (1993). Physically-based Modeling for Graphics and Vision.10 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.