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.
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
2021502 citationsChunliang Li, Kihyuk Sohn et al.profile →
A Spontaneous Micro-expression Database: Inducement, collection and baseline
2013435 citationsXiaobai Li, Tomas Pfister et al.profile →
Learning to Prompt for Continual Learning
2022329 citationsZifeng Wang, Zizhao Zhang et al.profile →
Flowing ConvNets for Human Pose Estimation in Videos
2015309 citationsTomas Pfister, James Charles et al.profile →
This map shows the geographic impact of Tomas Pfister'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 Tomas Pfister with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Tomas Pfister more than expected).
This network shows the impact of papers produced by Tomas Pfister. 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 Tomas Pfister. The network helps show where Tomas Pfister may publish in the future.
Co-authorship network of co-authors of Tomas Pfister
This figure shows the co-authorship network connecting the top 25 collaborators of Tomas Pfister.
A scholar is included among the top collaborators of Tomas Pfister 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 Tomas Pfister. Tomas Pfister is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Hsieh, Cheng-Yu, Chunliang Li, Chih‐Kuan Yeh, et al.. (2023). Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes. 8003–8017.108 indexed citations breakdown →
Li, Chunliang, Kihyuk Sohn, Jinsung Yoon, & Tomas Pfister. (2021). CutPaste: Self-Supervised Learning for Anomaly Detection and Localization. 9659–9669.502 indexed citations breakdown →
11.
Zou, Yuliang, Zizhao Zhang, Han Zhang, et al.. (2021). PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. arXiv (Cornell University).126 indexed citations
12.
Sohn, Kihyuk, et al.. (2021). Learning and Evaluating Representations for Deep One-Class Classification. International Conference on Learning Representations.2 indexed citations
13.
Arık, Sercan Ö., Chunliang Li, Jinsung Yoon, et al.. (2020). Interpretable sequence learning for COVID-19 forecasting. Neural Information Processing Systems. 33. 18807–18818.9 indexed citations
14.
Yoon, Jinsung, Sercan Ö. Arık, & Tomas Pfister. (2020). Data Valuation using Reinforcement Learning. International Conference on Machine Learning. 1. 10842–10851.9 indexed citations
15.
Xie, Yujia, Hanjun Dai, Bo Dai, et al.. (2020). Differentiable Top-k with Optimal Transport. Neural Information Processing Systems. 33. 20520–20531.17 indexed citations
16.
Arık, Sercan Ö. & Tomas Pfister. (2019). Attention-Based Prototypical Learning Towards Interpretable, Confident and Robust Deep Neural Networks.. arXiv (Cornell University).4 indexed citations
17.
Zhang, Zizhao, Han Zhang, Sercan Ö. Arık, Honglak Lee, & Tomas Pfister. (2019). IEG: Robust Neural Network Training to Tackle Severe Label Noise.. arXiv (Cornell University).1 indexed citations
18.
Zhu, Linchao, Sercan Ö. Arık, Yi Yang, & Tomas Pfister. (2019). Learning to Transfer Learn. arXiv (Cornell University).2 indexed citations
Pfister, Tomas, James Charles, & Andrew Zisserman. (2013). Large-scale Learning of Sign Language by Watching TV (Using Co-occurrences).. British Machine Vision Conference.28 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.