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.
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
20141.5k citationsMykhaylo Andriluka, Leonid Pishchulin et al.profile →
Towards Total Recall in Industrial Anomaly Detection
2022622 citationsKarsten Roth, Latha Pemula et al.2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)profile →
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
2016622 citationsLeonid Pishchulin, Eldar Insafutdinov et al.profile →
On feature combination for multiclass object classification
2009577 citationsPeter Gehler, Sebastian Nowozinprofile →
Unite the People: Closing the Loop Between 3D and 2D Human Representations
2017293 citationsMartin Kiefel, Peter Gehler 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 Peter Gehler'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 Peter Gehler with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Peter Gehler more than expected).
This network shows the impact of papers produced by Peter Gehler. 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 Peter Gehler. The network helps show where Peter Gehler may publish in the future.
Co-authorship network of co-authors of Peter Gehler
This figure shows the co-authorship network connecting the top 25 collaborators of Peter Gehler.
A scholar is included among the top collaborators of Peter Gehler 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 Peter Gehler. Peter Gehler is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Roth, Karsten, Latha Pemula, Joaquin Zepeda, et al.. (2022). Towards Total Recall in Industrial Anomaly Detection. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 14298–14308.622 indexed citations breakdown →
2.
Wüthrich, Manuel, Peter Gehler, Ole Winther, et al.. (2021). The Role of Pretrained Representations for the OOD Generalization of RL Agents. arXiv (Cornell University).2 indexed citations
3.
Kügelgen, Julius von, et al.. (2021). Backward-Compatible Prediction Updates: A Probabilistic Approach. Cambridge University Engineering Department Publications Database. 34.1 indexed citations
4.
Tulyakov, Stepan, François Fleuret, Martin Kiefel, Peter Gehler, & Michael Hirsch. (2019). Learning an event sequence embedding for event-based deep stereo.1 indexed citations
Pishchulin, Leonid, Eldar Insafutdinov, Siyu Tang, et al.. (2016). DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation. 4929–4937.622 indexed citations breakdown →
Andriluka, Mykhaylo, Leonid Pishchulin, Peter Gehler, & Bernt Schiele. (2014). 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. 3686–3693.1536 indexed citations breakdown →
12.
Jampani, Varun, Sebastian Nowozin, Matthew Loper, & Peter Gehler. (2014). The Informed Sampler: A Discriminative Approach to Bayesian Inference in Computer Vision. arXiv (Cornell University).1 indexed citations
13.
Nowozin, Sebastian, Peter Gehler, Jeremy Jancsary, & Christoph H. Lampert. (2014). Structured Prediction for Event Detection. 333–361.1 indexed citations
Dinuzzo, Francesco, Cheng Soon Ong, Gianluigi Pillonetto, & Peter Gehler. (2011). Learning Output Kernels with Block Coordinate Descent. Max Planck Institute for Plasma Physics. 49–56.38 indexed citations
18.
Rother, Carsten, Martin Kiefel, Lumin Zhang, Bernhard Schölkopf, & Peter Gehler. (2011). Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance. Neural Information Processing Systems. 24. 765–773.57 indexed citations
19.
Gehler, Peter & Olivier Chapelle. (2007). Deterministic Annealing for Multiple-Instance Learning. MPG.PuRe (Max Planck Society). 123–130.61 indexed citations
20.
Welling, Max & Peter Gehler. (2005). Products of ``Edge-perts. 18. 419–426.10 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.