262 citations
- ETH ZurichCH18 papers
- Microsoft (United States)US10 papers
- Chalmers University of TechnologySE4 papers
- Laboratory of Physical ChemistryCH3 papers
- Max Planck Institute for Intelligent SystemsDE3 papers
- Microsoft Research (United Kingdom)GB3 papers
- Technical University of MunichDE2 papers
- University of AmsterdamNL2 papers
- University of TübingenDE2 papers
- Amsterdam University of the ArtsNL1 paper
- Czech Technical University in PragueCZ1 paper
- DSO National LaboratoriesSG1 paper
Showing 2019Show all
2 papers · 1 filter
cs.CV2019★ 6 cited
Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
Huseyin Coskun, Zeeshan Zia, Bugra Tekin +4
The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot tran…
cs.CV2019★ 150 cited
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
Hermann Blum, Paul-Edouard Sarlin, Juan Nieto +2
Deep learning has enabled impressive progress in the accuracy of semantic segmentation. Yet, the ability to estimate uncertainty and detect failure is key for safety-critical appli…