Hilde Kuehne

6.2k total citations · 2 hit papers
33 papers, 3.2k citations indexed

About

Hilde Kuehne is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing. According to data from OpenAlex, Hilde Kuehne has authored 33 papers receiving a total of 3.2k indexed citations (citations by other indexed papers that have themselves been cited), including 25 papers in Computer Vision and Pattern Recognition, 17 papers in Artificial Intelligence and 4 papers in Signal Processing. Recurrent topics in Hilde Kuehne's work include Human Pose and Action Recognition (18 papers), Multimodal Machine Learning Applications (16 papers) and Domain Adaptation and Few-Shot Learning (8 papers). Hilde Kuehne is often cited by papers focused on Human Pose and Action Recognition (18 papers), Multimodal Machine Learning Applications (16 papers) and Domain Adaptation and Few-Shot Learning (8 papers). Hilde Kuehne collaborates with scholars based in Germany, United States and Austria. Hilde Kuehne's co-authors include T. Serre, Hueihan Jhuang, Estíbaliz Garrote, Tomaso Poggio, Jüergen Gall, Ali Bilgin Arslan, Alexander Richard, Tanja Schultz, Rogério Feris and Rainer Stiefelhagen and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Signal Processing Letters and Computer Vision and Image Understanding.

In The Last Decade

Hilde Kuehne

30 papers receiving 3.1k citations

Hit Papers

align trajectories

What are hit papers?

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.

HMDB: A large video database for human motion recognition

2011 2.3k citations Hilde Kuehne, T. Serre et al. profile →
The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities

2014 296 citations Hilde Kuehne, Ali Bilgin Arslan et al. Fraunhofer-Publica (Fraunhofer-Gesellschaft) profile →

Peers

Hilde Kuehne

CVPR

AI

BE

HI

EDM

Alexander Kläser China

Marcin Marszałek France

Víctor Escorcia Saudi Arabia

Xiaojiang Peng China

Daniel Weinland France

Christian Schüldt Sweden

Saihui Hou China

Fabian Caba Heilbron United States

Alexander Kläser China

Hilde Kuehne

3.4k ×1.2

CVPR

1.7k ×0.9

AI

937 ×1.5

BE

554 ×1.7

HI

88 ×0.6

EDM

Citations per year, relative to Hilde Kuehne Hilde Kuehne (= 1×) peers Alexander Kläser

Countries citing papers authored by Hilde Kuehne

Since Specialization

Citations

This map shows the geographic impact of Hilde Kuehne'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 Hilde Kuehne with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Hilde Kuehne more than expected).

Fields of papers citing papers by Hilde Kuehne

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Hilde Kuehne. 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 Hilde Kuehne. The network helps show where Hilde Kuehne may publish in the future.

Co-authorship network of co-authors of Hilde Kuehne

This figure shows the co-authorship network connecting the top 25 collaborators of Hilde Kuehne. A scholar is included among the top collaborators of Hilde Kuehne 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 Hilde Kuehne. Hilde Kuehne is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Rouditchenko, Andrew, Samuel Thomas, Hilde Kuehne, Rogério Feris, & James Glass. (2025). mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition. IEEE Signal Processing Letters. 32. 2144–2148.

2.

Nagrani, Arsha, et al.. (2025). Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks. 29050–29059.

3.

Kuehne, Hilde, et al.. (2024). WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies. 8(4). 1–21. 11 indexed citations

4.

Ferrari, Vittorio, et al.. (2024). Grounding Everything: Emerging Localization Properties in Vision-Language Transformers. 3828–3837. 15 indexed citations

5.

Chen, Brian, Andrew Rouditchenko, Daniel Kondermann, et al.. (2024). What, When, and Where? Self-Supervised Spatio- Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions. 18419–18429. 1 indexed citations

6.

Rouditchenko, Andrew, Yuan Gong, Samuel Thomas, et al.. (2024). Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation. 2420–2424. 6 indexed citations

7.

Karlinsky, Leonid, et al.. (2024). DASS: Distilled Audio State Space Models are Stronger and More Duration-Scalable Learners. 1015–1022. 2 indexed citations

8.

Kuehne, Hilde, et al.. (2023). Learning Situation Hyper-Graphs for Video Question Answering. 5 indexed citations

9.

Goldlüecke, Bastian, et al.. (2022). Style Agnostic 3D Reconstruction via Adversarial Style Transfer. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2273–2282. 2 indexed citations

10.

Harary, Sivan, Eli Schwartz, Assaf Arbelle, et al.. (2022). Unsupervised Domain Generalization by Learning a Bridge Across Domains. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5270–5280. 18 indexed citations

11.

Chen, Brian, Andrew Rouditchenko, Hilde Kuehne, et al.. (2021). Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 7992–8001. 46 indexed citations

12.

Rouditchenko, Andrew, David Harwath, Samuel Thomas, et al.. (2021). Cascaded Multilingual Audio-Visual Learning from Videos. 3006–3010. 4 indexed citations

13.

Kuehne, Hilde, Alexander Richard, & Jüergen Gall. (2018). A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 42(4). 765–779. 49 indexed citations

14.

Richard, Alexander, Hilde Kuehne, & Jüergen Gall. (2018). Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints. 5987–5996. 51 indexed citations

15.

Richard, Alexander, Hilde Kuehne, & Jüergen Gall. (2017). Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling. 1273–1282. 99 indexed citations

16.

Kuehne, Hilde, Alexander Richard, & Jüergen Gall. (2017). Weakly supervised learning of actions from transcripts. Computer Vision and Image Understanding. 163. 78–89. 65 indexed citations

17.

Kuehne, Hilde, Jüergen Gall, & T. Serre. (2016). An end-to-end generative framework for video segmentation and recognition. 1–8. 103 indexed citations

18.

Kuehne, Hilde, Ali Bilgin Arslan, & T. Serre. (2014). The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities. Fraunhofer-Publica (Fraunhofer-Gesellschaft). 780–787. 296 indexed citations breakdown →

19.

Kuehne, Hilde, et al.. (2011). Combined intention, activity, and motion recognition for a humanoid household robot. 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. 18 indexed citations

20.

Kuehne, Hilde, et al.. (2009). HMM-based human motion recognition with optical flow data. 50. 425–430. 22 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.

Explore authors with similar magnitude of impact