Matches in SemOpenAlex for { <https://semopenalex.org/work/W2954404989> ?p ?o ?g. }
- W2954404989 abstract "In this thesis, two hierarchical learning representations are explored in computer vision tasks. First, a novel graph theoretic method for statistical shape analysis, called Compositional Hierarchy of Parts (CHOP), was proposed. The method utilises line-based features as its building blocks for the representation of shapes. A deep, multi-layer vocabulary is learned by recursively compressing this initial representation. The key contribution of this work is to formulate layerwise learning as a frequent sub-graph discovery problem, solved using the Minimum Description Length (MDL) principle. The experiments show that CHOP employs part shareability and data compression features, and yields state-of- the-art shape retrieval performance on 3 benchmark datasets. In the second part of the thesis, a hybrid generative-evaluative method was used to solve the dexterous grasping problem. This approach combines a learned dexterous grasp generation model with two novel evaluative models based on Convolutional Neural Networks (CNNs). The data- efficient generative method learns from a human demonstrator. The evaluative models are trained in simulation, using the grasps proposed by the generative approach and the depth images of the objects from a single view. On a real grasp dataset of 49 scenes with previously unseen objects, the proposed hybrid architecture outperforms the purely generative method, with a grasp success rate of 77.7% to 57.1%. The thesis concludes by comparing the two families of deep architectures, compositional hierarchies and DNNs, providing insights on their strengths and weaknesses." @default.
- W2954404989 created "2019-07-12" @default.
- W2954404989 creator A5016829751 @default.
- W2954404989 date "2018-12-01" @default.
- W2954404989 modified "2023-09-26" @default.
- W2954404989 title "Learning deep representations for robotics applications" @default.
- W2954404989 cites W1022526533 @default.
- W2954404989 cites W1481988000 @default.
- W2954404989 cites W1503925285 @default.
- W2954404989 cites W1510186039 @default.
- W2954404989 cites W1548575572 @default.
- W2954404989 cites W1549675037 @default.
- W2954404989 cites W1555614281 @default.
- W2954404989 cites W1561092886 @default.
- W2954404989 cites W1597861020 @default.
- W2954404989 cites W1600556920 @default.
- W2954404989 cites W1635415043 @default.
- W2954404989 cites W1660390307 @default.
- W2954404989 cites W1686810756 @default.
- W2954404989 cites W1794703952 @default.
- W2954404989 cites W1799366690 @default.
- W2954404989 cites W1820657498 @default.
- W2954404989 cites W1849277567 @default.
- W2954404989 cites W1861492603 @default.
- W2954404989 cites W1892339738 @default.
- W2954404989 cites W189596042 @default.
- W2954404989 cites W1904365287 @default.
- W2954404989 cites W1905882502 @default.
- W2954404989 cites W1960289438 @default.
- W2954404989 cites W1965080940 @default.
- W2954404989 cites W1968001820 @default.
- W2954404989 cites W1972094833 @default.
- W2954404989 cites W1975951726 @default.
- W2954404989 cites W1978131245 @default.
- W2954404989 cites W1978580730 @default.
- W2954404989 cites W1980602022 @default.
- W2954404989 cites W1981667747 @default.
- W2954404989 cites W1985641335 @default.
- W2954404989 cites W1988229958 @default.
- W2954404989 cites W1994197834 @default.
- W2954404989 cites W1994906459 @default.
- W2954404989 cites W1995444699 @default.
- W2954404989 cites W1995707608 @default.
- W2954404989 cites W1996611764 @default.
- W2954404989 cites W1999156278 @default.
- W2954404989 cites W1999160507 @default.
- W2954404989 cites W1999801207 @default.
- W2954404989 cites W2006208182 @default.
- W2954404989 cites W2007972795 @default.
- W2954404989 cites W2008909198 @default.
- W2954404989 cites W2011685039 @default.
- W2954404989 cites W2019377328 @default.
- W2954404989 cites W2019788814 @default.
- W2954404989 cites W2020719522 @default.
- W2954404989 cites W2025768430 @default.
- W2954404989 cites W2031489346 @default.
- W2954404989 cites W2033012377 @default.
- W2954404989 cites W2036163530 @default.
- W2954404989 cites W2040870580 @default.
- W2954404989 cites W2043003570 @default.
- W2954404989 cites W2045798786 @default.
- W2954404989 cites W2047085460 @default.
- W2954404989 cites W205159212 @default.
- W2954404989 cites W2054658115 @default.
- W2954404989 cites W2055132753 @default.
- W2954404989 cites W2057175746 @default.
- W2954404989 cites W2057493164 @default.
- W2954404989 cites W2063533050 @default.
- W2954404989 cites W2064878003 @default.
- W2954404989 cites W2068641309 @default.
- W2954404989 cites W2071107046 @default.
- W2954404989 cites W2071128523 @default.
- W2954404989 cites W2074302716 @default.
- W2954404989 cites W2076063813 @default.
- W2954404989 cites W2076398395 @default.
- W2954404989 cites W2077287201 @default.
- W2954404989 cites W2080171500 @default.
- W2954404989 cites W2085261163 @default.
- W2954404989 cites W2085302753 @default.
- W2954404989 cites W2085949256 @default.
- W2954404989 cites W2087514981 @default.
- W2954404989 cites W2088043683 @default.
- W2954404989 cites W2090042335 @default.
- W2954404989 cites W2093656888 @default.
- W2954404989 cites W2095705004 @default.
- W2954404989 cites W2097099483 @default.
- W2954404989 cites W2097117768 @default.
- W2954404989 cites W2097290407 @default.
- W2954404989 cites W2098580305 @default.
- W2954404989 cites W2099471712 @default.
- W2954404989 cites W2099972257 @default.
- W2954404989 cites W2100398441 @default.
- W2954404989 cites W2100495367 @default.
- W2954404989 cites W2101926813 @default.
- W2954404989 cites W2102605133 @default.
- W2954404989 cites W2104408738 @default.
- W2954404989 cites W2104431043 @default.
- W2954404989 cites W2106255337 @default.
- W2954404989 cites W2106270058 @default.
- W2954404989 cites W2106404777 @default.