Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Daniel Prusa"'
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031264115
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3ee9a8bf2762f2e02ff1b81cada3f42
https://doi.org/10.1007/978-3-031-26412-2_27
https://doi.org/10.1007/978-3-031-26412-2_27
Publikováno v:
CVPR
It is well-known that for general convex optimization problems, block-coordinate descent can get stuck in poor local optima. Despite that, versions of this method known as convergent message passing are very successful to approximately solve the dual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a8583c0af3ceaf7b23f57b2c4429a35
https://doi.org/10.1109/cvpr42600.2020.00758
https://doi.org/10.1109/cvpr42600.2020.00758
Autor:
Tomáš Werner, Daniel Prusa
Publikováno v:
CVPR
We show that solving the LP relaxation of the min-sum labeling problem (also known as MAP inference problem in graphical models, discrete energy minimization, or valued constraint satisfaction) is not easier than solving any linear program. Precisely
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc4b01387cf55240f7be5a4e89e46ccc
https://doi.org/10.1109/tpami.2014.2353626
https://doi.org/10.1109/tpami.2014.2353626
Autor:
Daniel Prusa, Akio Fujiyoshi
Publikováno v:
ICDAR
We study the task of document layout analysis based on two-dimensional context-free grammars. We first identify a subclass of the grammars sufficient for a document structure description where productions follow a mechanism inducing regular languages
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa249f9165f029aabcd12f992dc0fc78
https://doi.org/10.1109/icdar.2017.185
https://doi.org/10.1109/icdar.2017.185
Publikováno v:
ICFHR
We experiment with off-line recognition of handwritten flowcharts based on strokes reconstruction and our state-of-the-art on-line diagram recognizer. A simple baseline algorithm for strokes reconstruction is presented and necessary modifications of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::42cb50d8c3006b5edad28a7a5d1e3bc7
https://doi.org/10.1109/icfhr.2016.0022
https://doi.org/10.1109/icfhr.2016.0022
Autor:
Daniel Prusa, Tomáš Werner
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 39(7)
In our recent work, we showed that solving the LP relaxation of the pairwise min-sum labeling problem (also known as MAP inference in graphical models or discrete energy minimization) is not much easier than solving any linear program. Precisely, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a1da06a40a6cb76572bdb230e49159a
https://pubmed.ncbi.nlm.nih.gov/27333598
https://pubmed.ncbi.nlm.nih.gov/27333598
Autor:
Daniel Prusa
Publikováno v:
CVPR
We show how the simplex algorithm can be tailored to the linear programming relaxation of pairwise energy minimization with binary variables. A special structure formed by basic and nonbasic variables in each stage of the algorithm is identified and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::996ac80d3d7c9d53cea27206d8d70db1
https://doi.org/10.1109/cvpr.2015.7298645
https://doi.org/10.1109/cvpr.2015.7298645
Publikováno v:
WACV
This paper deals with recognition of arrows in online sketched diagrams. Arrows have varying appearance and thus it is a difficult task to recognize them directly. It is beneficial to detect arrows after other symbols (easier to detect) are already f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7afedac701f220a82f2f529783204bb1
https://doi.org/10.1109/wacv.2015.87
https://doi.org/10.1109/wacv.2015.87
Publikováno v:
ICFHR
We present our recent model of a diagram recognition engine. It extends our previous work which approaches the structural recognition as an optimization problem of choosing the best subset of symbol candidates. The main improvement is the integration
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2006b9732585b46815346ae991e1d781
https://doi.org/10.1109/icfhr.2014.100
https://doi.org/10.1109/icfhr.2014.100
Publikováno v:
ICDAR
This work deals with the on-line recognition of hand-drawn graphical sketches with structure. We present a novel approach, in which the search for a suitable interpretation of the input is formulated as a combinatorial optimization task - the max-sum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3a0c44c3475dd5ce13da0974781482c