Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794602004> ?p ?o ?g. }
- W2794602004 abstract "The paper adopts two different convolution sampling paths: from large scale to small scale sampling (top-down) and small scale to large scale sampling (bottom-up), and propose the top-down sampling convolution neural network for face segmentation (TDNN). On the LFW and the Helen dataset, it is demonstrated about the advantage of face segmentation by TDNN. In addition, the shared weight is added to each convolution integral, we propose TDNN with shared weight (TDNNSW). On the Helen dataset, TDNNSW with shared weight further improves the accuracy of face segmentation. Since TDNN is trained end-to-end, our model has advantageous properties such as less parameters and more rapid calculation for face segmentation." @default.
- W2794602004 created "2018-04-06" @default.
- W2794602004 creator A5049142552 @default.
- W2794602004 date "2017-12-01" @default.
- W2794602004 modified "2023-09-23" @default.
- W2794602004 title "Top-down sampling convolution network for face segmentation" @default.
- W2794602004 cites W1903029394 @default.
- W2794602004 cites W1905033729 @default.
- W2794602004 cites W1976948919 @default.
- W2794602004 cites W1980163762 @default.
- W2794602004 cites W2114096665 @default.
- W2794602004 cites W2175578667 @default.
- W2794602004 cites W2295744361 @default.
- W2794602004 cites W2301358467 @default.
- W2794602004 cites W2306289963 @default.
- W2794602004 cites W2307770531 @default.
- W2794602004 cites W2309415944 @default.
- W2794602004 cites W2317851288 @default.
- W2794602004 cites W2337199865 @default.
- W2794602004 cites W2337429362 @default.
- W2794602004 cites W2341907540 @default.
- W2794602004 cites W2408429073 @default.
- W2794602004 cites W2412782625 @default.
- W2794602004 cites W2508829638 @default.
- W2794602004 cites W2526041965 @default.
- W2794602004 cites W2558302927 @default.
- W2794602004 cites W2560023338 @default.
- W2794602004 cites W2560533888 @default.
- W2794602004 cites W2574651848 @default.
- W2794602004 cites W2582248455 @default.
- W2794602004 cites W2586748754 @default.
- W2794602004 cites W2962889061 @default.
- W2794602004 cites W2963253279 @default.
- W2794602004 cites W2963299740 @default.
- W2794602004 cites W2963420948 @default.
- W2794602004 cites W2963563573 @default.
- W2794602004 cites W2963739249 @default.
- W2794602004 cites W2964081403 @default.
- W2794602004 cites W2964114915 @default.
- W2794602004 doi "https://doi.org/10.1109/compcomm.2017.8322867" @default.
- W2794602004 hasPublicationYear "2017" @default.
- W2794602004 type Work @default.
- W2794602004 sameAs 2794602004 @default.
- W2794602004 citedByCount "2" @default.
- W2794602004 countsByYear W27946020042020 @default.
- W2794602004 countsByYear W27946020042021 @default.
- W2794602004 crossrefType "proceedings-article" @default.
- W2794602004 hasAuthorship W2794602004A5049142552 @default.
- W2794602004 hasConcept C106131492 @default.
- W2794602004 hasConcept C140779682 @default.
- W2794602004 hasConcept C144024400 @default.
- W2794602004 hasConcept C153180895 @default.
- W2794602004 hasConcept C154945302 @default.
- W2794602004 hasConcept C205649164 @default.
- W2794602004 hasConcept C2778755073 @default.
- W2794602004 hasConcept C2779304628 @default.
- W2794602004 hasConcept C31510193 @default.
- W2794602004 hasConcept C31972630 @default.
- W2794602004 hasConcept C36289849 @default.
- W2794602004 hasConcept C41008148 @default.
- W2794602004 hasConcept C45347329 @default.
- W2794602004 hasConcept C50644808 @default.
- W2794602004 hasConcept C58640448 @default.
- W2794602004 hasConcept C81363708 @default.
- W2794602004 hasConcept C89600930 @default.
- W2794602004 hasConceptScore W2794602004C106131492 @default.
- W2794602004 hasConceptScore W2794602004C140779682 @default.
- W2794602004 hasConceptScore W2794602004C144024400 @default.
- W2794602004 hasConceptScore W2794602004C153180895 @default.
- W2794602004 hasConceptScore W2794602004C154945302 @default.
- W2794602004 hasConceptScore W2794602004C205649164 @default.
- W2794602004 hasConceptScore W2794602004C2778755073 @default.
- W2794602004 hasConceptScore W2794602004C2779304628 @default.
- W2794602004 hasConceptScore W2794602004C31510193 @default.
- W2794602004 hasConceptScore W2794602004C31972630 @default.
- W2794602004 hasConceptScore W2794602004C36289849 @default.
- W2794602004 hasConceptScore W2794602004C41008148 @default.
- W2794602004 hasConceptScore W2794602004C45347329 @default.
- W2794602004 hasConceptScore W2794602004C50644808 @default.
- W2794602004 hasConceptScore W2794602004C58640448 @default.
- W2794602004 hasConceptScore W2794602004C81363708 @default.
- W2794602004 hasConceptScore W2794602004C89600930 @default.
- W2794602004 hasLocation W27946020041 @default.
- W2794602004 hasOpenAccess W2794602004 @default.
- W2794602004 hasPrimaryLocation W27946020041 @default.
- W2794602004 hasRelatedWork W2127207273 @default.
- W2794602004 hasRelatedWork W2189042576 @default.
- W2794602004 hasRelatedWork W2738221750 @default.
- W2794602004 hasRelatedWork W2773412982 @default.
- W2794602004 hasRelatedWork W2775456924 @default.
- W2794602004 hasRelatedWork W2796827446 @default.
- W2794602004 hasRelatedWork W2888506104 @default.
- W2794602004 hasRelatedWork W2952812791 @default.
- W2794602004 hasRelatedWork W2953206417 @default.
- W2794602004 hasRelatedWork W2989990962 @default.
- W2794602004 hasRelatedWork W3003111497 @default.
- W2794602004 hasRelatedWork W3010343303 @default.
- W2794602004 hasRelatedWork W3022728207 @default.
- W2794602004 hasRelatedWork W3088048803 @default.
- W2794602004 hasRelatedWork W3113357150 @default.