Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Elmar Haußmann"'
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 23:14741-14752
Deep Neural Networks (DNNs) often rely on very large datasets for training. Given the large size of such datasets, it is conceivable that they contain certain samples that either do not contribute or negatively impact the DNN's optimization. Modifyin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b6944ae54d5ebfe0dbb0b8f6358d255
https://doi.org/10.1109/tits.2021.3133268
https://doi.org/10.1109/tits.2021.3133268
Autor:
Suraj Kothawade, Donna Roy, Michele Fenzi, Elmar Haussmann, Jose M. Alvarez, Christoph Angerer
Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned model or mitigating class imba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2dd231017ff9e3f5d9d9abb45a15c1f3
http://arxiv.org/abs/2207.01778
http://arxiv.org/abs/2207.01778
Autor:
Kashyap Chitta, Jose M. Alvarez, Hanson Xu, Akshita Mittel, Nicolas Koumchatzky, Elmar Haussmann, Michele Fenzi, Clement Farabet, Donna Roy, Jan Ivanecky
Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled data is already a major undertaking, only a subset of it can be labeled
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9ff319c9778fbac967127e6ca4217562
Publikováno v:
KI - Künstliche Intelligenz. 32:19-26
We provide a quality evaluation of KB+Text search, a deep integration of knowledge base search and standard full-text search. A knowledge base (KB) is a set of subject–predicate–object triples with a common naming scheme. The standard query langu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3b3f65fa5643a659a88bca229a28b4c
https://doi.org/10.1007/s13218-017-0513-9
https://doi.org/10.1007/s13218-017-0513-9
Publikováno v:
Foundations and Trends® in Information Retrieval. 10:119-271
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ecd5dd376e1cdcd377ed3c759d37adae
https://doi.org/10.1561/1500000032
https://doi.org/10.1561/1500000032
Publikováno v:
WSDM
The WSDM Cup 2017 was a data mining challenge held in conjunction with the 10th International Conference on Web Search and Data Mining (WSDM). It addressed key challenges of knowledge bases today: quality assurance and entity search. For quality assu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f179a574039ef284d083c2f0a62b4040
https://doi.org/10.1145/3018661.3022762
https://doi.org/10.1145/3018661.3022762
This monograph provides a comprehensive overview of the broad area of semantic search on text and knowledge bases. In a nutshell, semantic search is'search with meaning'. This'meaning'can refer to various parts of the search process: understanding th
Autor:
Peter Thiemann, Faisal Aslam, Zartash Afzal Uzmi, Elmar Haussmann, Christian Schindelhauer, Mubashir Adnan Qureshi, Luminous Fennell, Ghufran Baig
Publikováno v:
LCTES
The ability of tiny embedded devices to run large feature-rich programs is typically constrained by the amount of memory installed on such devices. Furthermore, the useful operation of these devices in wireless sensor applications is limited by their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7ece0bdd0732689ff65c0e43cec49a7
https://doi.org/10.1145/2345141.2248420
https://doi.org/10.1145/2345141.2248420
Autor:
Hannah Bast, Elmar Haussmann
Publikováno v:
CIKM
Real-world factoid or list questions often have a simple structure, yet are hard to match to facts in a given knowledge base due to high representational and linguistic variability. For example, to answer "who is the ceo of apple" on Freebase require
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31a68717ca88e9e3ac301446d290b3ce
https://doi.org/10.1145/2806416.2806472
https://doi.org/10.1145/2806416.2806472
Publikováno v:
SIGIR
We compute and evaluate relevance scores for knowledge-base triples from type-like relations. Such a score measures the degree to which an entity "belongs" to a type. For example, Quentin Tarantino has various professions, including Film Director, Sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8f019fb643a999da92553d699a6a70cd
https://doi.org/10.1145/2766462.2767734
https://doi.org/10.1145/2766462.2767734