Search Results for author: Achim Rettinger

Found 15 papers, 1 papers with code

Context-driven Visual Object Recognition based on Knowledge Graphs

no code implementations20 Oct 2022 Sebastian Monka, Lavdim Halilaj, Achim Rettinger

The experimental results provide evidence that the contextual views influence the image representations in the DNN differently and therefore lead to different predictions for the same images.

Knowledge Graphs Object Recognition +1

Signing the Supermask: Keep, Hide, Invert

1 code implementation ICLR 2022 Nils Koster, Oliver Grothe, Achim Rettinger

Through this extension and adaptations of initialization methods, we achieve a pruning rate of up to 99%, while still matching or exceeding the performance of various baseline and previous models.

A Survey on Visual Transfer Learning using Knowledge Graphs

no code implementations27 Jan 2022 Sebastian Monka, Lavdim Halilaj, Achim Rettinger

KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding.

Knowledge Graph Embedding Knowledge Graphs +1

Learning Visual Models using a Knowledge Graph as a Trainer

no code implementations17 Feb 2021 Sebastian Monka, Lavdim Halilaj, Stefan Schmid, Achim Rettinger

However, due to the sole dependence on the image data distribution of the training domain, these models tend to fail when applied to a target domain that differs from their source domain.

Knowledge Graph Embedding Knowledge Graphs +2

Towards Learning Cross-Modal Perception-Trace Models

no code implementations18 Oct 2019 Achim Rettinger, Viktoria Bogdanova, Philipp Niemann

In this paper we empirically investigate the difference between human perception and context heuristics of basic embedding models.

Knowledge Graphs Link Prediction +1

Which Knowledge Graph Is Best for Me?

no code implementations28 Sep 2018 Michael Färber, Achim Rettinger

Furthermore, we proposed a framework for finding the most suitable knowledge graph for a given setting.

Knowledge Graphs

Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings

no code implementations25 Oct 2017 Aditya Mogadala, Dominik Jung, Achim Rettinger

But the gap in word usage between informal social media content such as tweets and diligently written content (e. g. news articles) make such assembling difficult.

Word Embeddings

Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance

no code implementations17 Oct 2017 Aditya Mogadala, Umanga Bista, Lexing Xie, Achim Rettinger

Images in the wild encapsulate rich knowledge about varied abstract concepts and cannot be sufficiently described with models built only using image-caption pairs containing selected objects.

RECSA: Resource for Evaluating Cross-lingual Semantic Annotation

no code implementations LREC 2014 Achim Rettinger, Lei Zhang, Da{\v{s}}a Berovi{\'c}, Danijela Merkler, Matea Sreba{\v{c}}i{\'c}, Marko Tadi{\'c}

To support this line of research we developed what we believe could serve as a gold standard Resource for Evaluating Cross-lingual Semantic Annotation (RECSA).

Machine Translation

xLiD-Lexica: Cross-lingual Linked Data Lexica

no code implementations LREC 2014 Lei Zhang, Michael F{\"a}rber, Achim Rettinger

In this paper, we introduce our cross-lingual linked data lexica, called xLiD-Lexica, which are constructed by exploiting the multilingual Wikipedia and linked data resources from Linked Open Data (LOD).

Cross-Lingual Entity Linking Entity Linking +3

Cannot find the paper you are looking for? You can Submit a new open access paper.