no code implementations • 17 Jun 2023 • Aditya Aditya, Bharat Lohani, Jagannath Aryal, Stephan Winter
PointMetaBase and KPConv (omni-supervised) achieve the highest mIoU on the Chandigarh (95. 24%) and Toronto3D datasets (91. 26%), respectively while PointCNN provides the highest mIoU on the Kerala dataset (85. 68%).
1 code implementation • 6 May 2022 • Ehsan Hamzei, Martin Tomko, Stephan Winter
Many place-related questions can only be answered by complex spatial reasoning, a task poorly supported by factoid question retrieval.
1 code implementation • 21 Jan 2021 • Ehsan Hamzei, Stephan Winter, Martin Tomko
In this paper, we present templates that allow to characterize the human-generated answers and to imitate their structure.
no code implementations • 17 Aug 2018 • Hao Chen, Maria Vasardani, Stephan Winter
Everyday place descriptions often contain place names of fine-grained features, such as buildings or businesses, that are more difficult to disambiguate than names referring to larger places, for example cities or natural geographic features.
no code implementations • 9 Oct 2017 • Hao Chen, Maria Vasardani, Stephan Winter
Current techniques for geo-referencing places from text documents are using place name recognition and disambiguation; however, place descriptions often contain place references that are not known by gazetteers, or that are expressed in other, more flexible ways.