Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Michael Donoser"'
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f5f0410993677a0dbbf3cf03ed7e2417
https://doi.org/10.1109/iccv48922.2021.01193
https://doi.org/10.1109/iccv48922.2021.01193
Publikováno v:
CVPR Workshops
Fashion retrieval methods aim at learning a clothing-specific embedding space where images are ranked based on their global visual similarity with a given query. How-ever, global embeddings struggle to capture localized fine-grained similarities betw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::746106cb4a1b869ed68b914339b117b0
https://doi.org/10.1109/cvprw53098.2021.00435
https://doi.org/10.1109/cvprw53098.2021.00435
Publikováno v:
CVPR
Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast amounts of digital cooking recipes and food images to train machine learning models. In this w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b614135b2dc25b9ad9937c9a31bf1a3
Publikováno v:
ICCV Workshops
The emergence of online influencers, the explosion of video content, and the massive amount of movie collections have served as an advertising vehicle for the fashion industry. This trend has created the need for automated methods that recognize peop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0c667a51e7f9d532e9acb78fb62dabe
https://doi.org/10.1109/iccvw.2019.00385
https://doi.org/10.1109/iccvw.2019.00385
Publikováno v:
Computer Vision and Image Understanding. 116:1149-1158
In this paper we propose a novel, game-theoretic approach for finding multiple instances of an object category as sets of mutually coherent votes in a generalized Hough space. Existing Hough-voting based detection systems have to inherently apply par
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3cab0f6456af08f62357ce1424ab59ef
https://doi.org/10.1016/j.cviu.2012.08.003
https://doi.org/10.1016/j.cviu.2012.08.003
Publikováno v:
Journal of Microscopy. 242:197-205
Summary A better understanding of paper properties requires a detailed knowledge about the spatial arrangement of its constituent materials in its structure. This paper presents a novel approach for the analysis of the three-dimensional paper structu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9272db6192f7d0c0db2c2b97c3aae72f
https://doi.org/10.1111/j.1365-2818.2010.03459.x
https://doi.org/10.1111/j.1365-2818.2010.03459.x
Publikováno v:
TU Graz
In this work we propose the use of contextual information provided by web search engine queries for improving text recognition performance. We first describe a framework for automated text recognition from images. It is based on detecting text areas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ce21f4f8a9f80c56dfa6008157a79cd
https://doi.org/10.1016/j.patrec.2009.10.003
https://doi.org/10.1016/j.patrec.2009.10.003
Publikováno v:
IPSJ Transactions on Computer Vision and Applications. 2:224-234
This paper introduces a novel efficient partial shape matching method named IS-Match. We use sampled points from the silhouette as a shape representation. The sampled points can be ordered which in turn allows to formulate the matching step as an ord
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::99b70f274a2407b1a54898473b881917
https://doi.org/10.2197/ipsjtcva.2.224
https://doi.org/10.2197/ipsjtcva.2.224
Publikováno v:
CHI
We present a system which automatically transfers printed technical documentation, such as handbooks, to three-dimensional Augmented Reality. Our system identifies the most frequent forms of instructions found in printed documentation, such as image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::040eb7a633cf1fcb97fb1e17d6ed84ef
https://doi.org/10.1145/2702123.2702490
https://doi.org/10.1145/2702123.2702490
Publikováno v:
Pattern Recognition Letters. 83:241-242
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8c54786ce62743f76b6ef225a83d3aa
https://doi.org/10.1016/j.patrec.2016.08.007
https://doi.org/10.1016/j.patrec.2016.08.007