Matches in SemOpenAlex for { <https://semopenalex.org/work/W2516963722> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2516963722 abstract "CNN has shown excellent performance on object recognition based on huge amount of real images. For training with synthetic data rendered from 3D models alone to reduce the workload of collecting real images, we propose a concatenated self-restraint learning structure lead by a triplet and softmax jointed loss function for object recognition. Locally connected auto encoder trained from rendered images with and without background used for object reconstruction against environment variables produces an additional channel automatically concatenated to RGB channels as input of classification network. This structure makes it possible training a softmax classifier directly from CNN based on synthetic data with our rendering strategy. Our structure halves the gap between training based on real photos and 3D model in both PASCAL and ImageNet database compared to GoogleNet." @default.
- W2516963722 created "2016-09-16" @default.
- W2516963722 creator A5025452586 @default.
- W2516963722 creator A5079490872 @default.
- W2516963722 date "2016-09-01" @default.
- W2516963722 modified "2023-09-25" @default.
- W2516963722 title "Self-restraint object recognition by model based CNN learning" @default.
- W2516963722 cites W1526868886 @default.
- W2516963722 cites W1591870335 @default.
- W2516963722 cites W1769599646 @default.
- W2516963722 cites W1942214758 @default.
- W2516963722 cites W1975517671 @default.
- W2516963722 cites W2010625607 @default.
- W2516963722 cites W2016427216 @default.
- W2516963722 doi "https://doi.org/10.1109/icip.2016.7532438" @default.
- W2516963722 hasPublicationYear "2016" @default.
- W2516963722 type Work @default.
- W2516963722 sameAs 2516963722 @default.
- W2516963722 citedByCount "4" @default.
- W2516963722 countsByYear W25169637222017 @default.
- W2516963722 countsByYear W25169637222018 @default.
- W2516963722 countsByYear W25169637222023 @default.
- W2516963722 crossrefType "proceedings-article" @default.
- W2516963722 hasAuthorship W2516963722A5025452586 @default.
- W2516963722 hasAuthorship W2516963722A5079490872 @default.
- W2516963722 hasConcept C108583219 @default.
- W2516963722 hasConcept C153180895 @default.
- W2516963722 hasConcept C154945302 @default.
- W2516963722 hasConcept C188441871 @default.
- W2516963722 hasConcept C199360897 @default.
- W2516963722 hasConcept C205711294 @default.
- W2516963722 hasConcept C2776151529 @default.
- W2516963722 hasConcept C2781238097 @default.
- W2516963722 hasConcept C31972630 @default.
- W2516963722 hasConcept C41008148 @default.
- W2516963722 hasConcept C64876066 @default.
- W2516963722 hasConcept C75608658 @default.
- W2516963722 hasConcept C82990744 @default.
- W2516963722 hasConcept C95623464 @default.
- W2516963722 hasConceptScore W2516963722C108583219 @default.
- W2516963722 hasConceptScore W2516963722C153180895 @default.
- W2516963722 hasConceptScore W2516963722C154945302 @default.
- W2516963722 hasConceptScore W2516963722C188441871 @default.
- W2516963722 hasConceptScore W2516963722C199360897 @default.
- W2516963722 hasConceptScore W2516963722C205711294 @default.
- W2516963722 hasConceptScore W2516963722C2776151529 @default.
- W2516963722 hasConceptScore W2516963722C2781238097 @default.
- W2516963722 hasConceptScore W2516963722C31972630 @default.
- W2516963722 hasConceptScore W2516963722C41008148 @default.
- W2516963722 hasConceptScore W2516963722C64876066 @default.
- W2516963722 hasConceptScore W2516963722C75608658 @default.
- W2516963722 hasConceptScore W2516963722C82990744 @default.
- W2516963722 hasConceptScore W2516963722C95623464 @default.
- W2516963722 hasLocation W25169637221 @default.
- W2516963722 hasOpenAccess W2516963722 @default.
- W2516963722 hasPrimaryLocation W25169637221 @default.
- W2516963722 hasRelatedWork W1939557789 @default.
- W2516963722 hasRelatedWork W2007544051 @default.
- W2516963722 hasRelatedWork W2008001747 @default.
- W2516963722 hasRelatedWork W2026349903 @default.
- W2516963722 hasRelatedWork W2202279169 @default.
- W2516963722 hasRelatedWork W2807311372 @default.
- W2516963722 hasRelatedWork W2922421953 @default.
- W2516963722 hasRelatedWork W2975200075 @default.
- W2516963722 hasRelatedWork W2989988688 @default.
- W2516963722 hasRelatedWork W2557461402 @default.
- W2516963722 isParatext "false" @default.
- W2516963722 isRetracted "false" @default.
- W2516963722 magId "2516963722" @default.
- W2516963722 workType "article" @default.