Marcus Rohrbach
Impact in
- Computer Vision and Pattern Recognition top 0.05%
- Multimodal Machine Learning Applications
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Video Analysis and Summarization
- Video Surveillance and Tracking Methods
- Artificial Intelligence top 0.1%
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications
- Topic Modeling
Papers in
-
- Multimodal Machine Learning Applications 32
- Human Pose and Action Recognition 19
- Advanced Image and Video Retrieval Techniques 7
- Video Analysis and Summarization 5
- Advanced Neural Network Applications 4
-
- Domain Adaptation and Few-Shot Learning 19
- Natural Language Processing Techniques 8
- Topic Modeling 7
- Co-authors
- Trevor Darrell (11 shared papers)Kate Saenko (8 shared papers)Subhashini Venugopalan (5 shared papers)Lisa Anne Hendricks (5 shared papers)Sergio Guadarrama (2 shared papers)Jeff Donahue (2 shared papers)Bernt Schiele (11 shared papers)Yannis Kalantidis (5 shared papers)
- Journals
- IEEE Transactions on Pattern Analysis and Machine Intelligence (1 paper)Transactions of the Association for Computational Linguistics (1 paper)IEEE Transactions on Intelligent Transportation Systems (1 paper)International Journal of Computer Vision (1 paper)Max Planck Institute for Plasma Physics (2 papers)
- Partner nations
- United StatesIsraelGermany
In The Last Decade
Marcus Rohrbach
42 papers receiving 10.1k citations
Marcus Rohrbach's Hit Papers
Peers
Comparison fields: 5 of 178
- Computer Vision and Pattern Recognition 8.5k
- Artificial Intelligence 4.9k
- Human-Computer Interaction 522
- Signal Processing 410
- Media Technology 263
Countries citing papers authored by Marcus Rohrbach
This map shows the geographic impact of Marcus Rohrbach'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 Marcus Rohrbach with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Marcus Rohrbach more than expected).
Fields of papers citing papers by Marcus Rohrbach
This network shows the impact of papers produced by Marcus Rohrbach. 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 Marcus Rohrbach. The network helps show where Marcus Rohrbach may publish in the future.
Co-authors
The 25 scholars most cited alongside Marcus Rohrbach, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 42 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Long-term recurrent convolutional networks for visual recognition and description Hit paper breakdown → | 2015 | 3070 |
| 2 | Long-Term Recurrent Convolutional Networks for Visual Recognition and Description Hit paper breakdown → | 2016 | 1096 |
| 3 | Sequence to Sequence -- Video to Text Hit paper breakdown → | 2015 | 835 |
| 4 | Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution Hit paper breakdown → | 2019 | 439 |
| 5 | Graph-Based Global Reasoning Networks Hit paper breakdown → | 2019 | 364 |
| 6 | A database for fine grained activity detection of cooking activities Hit paper breakdown → | 2012 | 323 |
| 7 | Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images Hit paper breakdown → | 2015 | 323 |
| 8 | FLAVA: A Foundational Language And Vision Alignment Model Hit paper breakdown → | 2022 | 272 |
| 9 | 2013 | 260 | |
| 10 | A dataset for Movie Description Hit paper breakdown → | 2015 | 245 |
| 11 | 12-in-1: Multi-Task Vision and Language Representation Learning Hit paper breakdown → | 2020 | 244 |
| 12 | 2017 | 242 | |
| 13 | 2016 | 234 | |
| 14 | 2020 | 232 | |
| 15 | 2013 | 230 | |
| 16 | 2017 | 230 | |
| 17 | 2011 | 166 | |
| 18 | 2017 | 166 | |
| 19 | 2010 | 157 | |
| 20 | 2017 | 152 |
About Marcus Rohrbach
Marcus Rohrbach is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Language and Linguistics, Molecular Biology and Automotive Engineering, having authored 42 papers that have together received 10.5k indexed citations. Recurring topics across this work include Multimodal Machine Learning Applications (32 papers), Human Pose and Action Recognition (19 papers), Domain Adaptation and Few-Shot Learning (19 papers), Natural Language Processing Techniques (8 papers), Advanced Image and Video Retrieval Techniques (7 papers), Topic Modeling (7 papers), Video Analysis and Summarization (5 papers) and Advanced Neural Network Applications (4 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (8.5k citations), Artificial Intelligence (4.9k citations), Human-Computer Interaction (522 citations), Signal Processing (410 citations) and Media Technology (263 citations). Marcus Rohrbach has collaborated with scholars based in United States, Israel and Germany. Frequent co-authors include Trevor Darrell, Kate Saenko, Subhashini Venugopalan, Lisa Anne Hendricks, Sergio Guadarrama, Jeff Donahue, Bernt Schiele, Yannis Kalantidis, Ronghang Hu and Raymond J. Mooney. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Transactions of the Association for Computational Linguistics, IEEE Transactions on Intelligent Transportation Systems, International Journal of Computer Vision and Max Planck Institute for Plasma Physics.
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.