FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996479480> ?p ?o ?g. }

• W2996479480 abstract "Support vector machines (SVMs) have been successful in solving many computer vision tasks including image and video category recognition especially for small and mid-scale training problems. The principle of these non-parametric models is to learn hyperplanes that separate data belonging to different classes while maximizing their margins. However, SVMs constrain the learned hyperplanes to lie in the span of support vectors, fixed/taken from training data, and this reduces their representational power and may lead to limited generalization performances. In this paper, we relax this constraint and allow the support vectors to be learned (instead of being fixed/taken from training data) in order to better fit a given classification task. Our approach, referred to as deep total variation support vector machines, is parametric and relies on a novel deep architecture that learns not only the SVM and the kernel parameters but also the support vectors, resulting into highly effective classifiers. We also show (under a particular setting of the activation functions in this deep architecture) that a large class of kernels and their combinations can be learned. Experiments conducted on the challenging task of skeleton-based action recognition show the outperformance of our deep total variation SVMs w.r.t different baselines as well as the related work." @default.
• W2996479480 created "2019-12-26" @default.
• W2996479480 creator A5029896607 @default.
• W2996479480 date "2019-12-12" @default.
• W2996479480 modified "2023-09-27" @default.
• W2996479480 title "Totally Deep Support Vector Machines." @default.
• W2996479480 cites W1026270304 @default.
• W2996479480 cites W130653142 @default.
• W2996479480 cites W1496317909 @default.
• W2996479480 cites W1510073064 @default.
• W2996479480 cites W1546411676 @default.
• W2996479480 cites W1560724230 @default.
• W2996479480 cites W1560851690 @default.
• W2996479480 cites W1567012231 @default.
• W2996479480 cites W1575130722 @default.
• W2996479480 cites W1591394246 @default.
• W2996479480 cites W1601437336 @default.
• W2996479480 cites W1618905105 @default.
• W2996479480 cites W1663792126 @default.
• W2996479480 cites W1677182931 @default.
• W2996479480 cites W167790647 @default.
• W2996479480 cites W1751437809 @default.
• W2996479480 cites W1881452810 @default.
• W2996479480 cites W1944448017 @default.
• W2996479480 cites W1950788856 @default.
• W2996479480 cites W1967170228 @default.
• W2996479480 cites W1969117674 @default.
• W2996479480 cites W1992208818 @default.
• W2996479480 cites W1994935303 @default.
• W2996479480 cites W1998167411 @default.
• W2996479480 cites W2008056655 @default.
• W2996479480 cites W2017588182 @default.
• W2996479480 cites W2031489346 @default.
• W2996479480 cites W2039182213 @default.
• W2996479480 cites W2046991152 @default.
• W2996479480 cites W2049033299 @default.
• W2996479480 cites W2054103873 @default.
• W2996479480 cites W2058256495 @default.
• W2996479480 cites W2063907334 @default.
• W2996479480 cites W2070244236 @default.
• W2996479480 cites W2097117768 @default.
• W2996479480 cites W2102116870 @default.
• W2996479480 cites W2102605133 @default.
• W2996479480 cites W2104867159 @default.
• W2996479480 cites W2107008379 @default.
• W2996479480 cites W2107397716 @default.
• W2996479480 cites W2108745803 @default.
• W2996479480 cites W2109235804 @default.
• W2996479480 cites W2111073379 @default.
• W2996479480 cites W2112562896 @default.
• W2996479480 cites W2115708871 @default.
• W2996479480 cites W2117539524 @default.
• W2996479480 cites W2120515362 @default.
• W2996479480 cites W2123872146 @default.
• W2996479480 cites W2124351082 @default.
• W2996479480 cites W2126326837 @default.
• W2996479480 cites W2134778014 @default.
• W2996479480 cites W2136940668 @default.
• W2996479480 cites W2137055149 @default.
• W2996479480 cites W2139212933 @default.
• W2996479480 cites W2143426320 @default.
• W2996479480 cites W2144902422 @default.
• W2996479480 cites W2145287260 @default.
• W2996479480 cites W2145295623 @default.
• W2996479480 cites W2146798037 @default.
• W2996479480 cites W2147147599 @default.
• W2996479480 cites W2148603752 @default.
• W2996479480 cites W2150341604 @default.
• W2996479480 cites W2151802193 @default.
• W2996479480 cites W2152523366 @default.
• W2996479480 cites W2153635508 @default.
• W2996479480 cites W2154462399 @default.
• W2996479480 cites W2156137575 @default.
• W2996479480 cites W2156387975 @default.
• W2996479480 cites W2163605009 @default.
• W2996479480 cites W2164535072 @default.
• W2996479480 cites W2167608136 @default.
• W2996479480 cites W2169625877 @default.
• W2996479480 cites W2169966850 @default.
• W2996479480 cites W2194775991 @default.
• W2996479480 cites W2230000137 @default.
• W2996479480 cites W2282078507 @default.
• W2996479480 cites W2294422256 @default.
• W2996479480 cites W2299156643 @default.
• W2996479480 cites W2307035320 @default.
• W2996479480 cites W2395459784 @default.
• W2996479480 cites W2398955161 @default.
• W2996479480 cites W2399164823 @default.
• W2996479480 cites W2510185399 @default.
• W2996479480 cites W2548669413 @default.
• W2996479480 cites W2556782416 @default.
• W2996479480 cites W2557283755 @default.
• W2996479480 cites W2587063199 @default.
• W2996479480 cites W2591766052 @default.
• W2996479480 cites W2603861860 @default.
• W2996479480 cites W2604906478 @default.
• W2996479480 cites W2620572990 @default.
• W2996479480 cites W2756063524 @default.
• W2996479480 cites W2769171608 @default.
• W2996479480 cites W2802115575 @default.

• next