Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025128826> ?p ?o ?g. }
- W3025128826 endingPage "4786" @default.
- W3025128826 startingPage "4774" @default.
- W3025128826 abstract "A key objective in multi-view learning is to model the information common to multiple parallel views of a class of objects/events to improve downstream learning tasks. In this context, two open research questions remain: How can we model hundreds of views per event? Can we learn robust multi-view embeddings without any knowledge of how these views are acquired? We present a neural method based on multi-view correlation to capture the information shared across a large number of views by subsampling them in a view-agnostic manner during training. To provide an upper bound on the number of views to subsample for a given embedding dimension, we analyze the error of the bootstrapped multi-view correlation objective using matrix concentration theory. Our experiments on spoken word recognition, 3D object classification and pose-invariant face recognition demonstrate the robustness of view bootstrapping to model a large number of views. Results underscore the applicability of our method for a view-agnostic learning setting." @default.
- W3025128826 created "2020-05-21" @default.
- W3025128826 creator A5008305849 @default.
- W3025128826 creator A5010028928 @default.
- W3025128826 date "2021-01-01" @default.
- W3025128826 modified "2023-10-18" @default.
- W3025128826 title "Generalized Multiview Shared Subspace Learning Using View Bootstrapping" @default.
- W3025128826 cites W1197925356 @default.
- W3025128826 cites W144419643 @default.
- W3025128826 cites W1523385540 @default.
- W3025128826 cites W1644641054 @default.
- W3025128826 cites W1670132599 @default.
- W3025128826 cites W1731081199 @default.
- W3025128826 cites W1883346539 @default.
- W3025128826 cites W1920022804 @default.
- W3025128826 cites W1975077471 @default.
- W3025128826 cites W1990383128 @default.
- W3025128826 cites W2001619934 @default.
- W3025128826 cites W2011865252 @default.
- W3025128826 cites W2023925753 @default.
- W3025128826 cites W2025341678 @default.
- W3025128826 cites W2030899956 @default.
- W3025128826 cites W2034214321 @default.
- W3025128826 cites W2062125287 @default.
- W3025128826 cites W2071207147 @default.
- W3025128826 cites W2090101874 @default.
- W3025128826 cites W2101234009 @default.
- W3025128826 cites W2130866639 @default.
- W3025128826 cites W2130955819 @default.
- W3025128826 cites W2136148671 @default.
- W3025128826 cites W2142674578 @default.
- W3025128826 cites W2150769028 @default.
- W3025128826 cites W2153890400 @default.
- W3025128826 cites W2154415691 @default.
- W3025128826 cites W2186500555 @default.
- W3025128826 cites W2187089797 @default.
- W3025128826 cites W2222512263 @default.
- W3025128826 cites W2428757121 @default.
- W3025128826 cites W2516780539 @default.
- W3025128826 cites W2534244347 @default.
- W3025128826 cites W2590019597 @default.
- W3025128826 cites W2606011186 @default.
- W3025128826 cites W2620341577 @default.
- W3025128826 cites W2748488820 @default.
- W3025128826 cites W2752197020 @default.
- W3025128826 cites W2784996474 @default.
- W3025128826 cites W2797583228 @default.
- W3025128826 cites W2814803617 @default.
- W3025128826 cites W2883618873 @default.
- W3025128826 cites W2887500939 @default.
- W3025128826 cites W2892880750 @default.
- W3025128826 cites W2895191479 @default.
- W3025128826 cites W2898233200 @default.
- W3025128826 cites W2905173041 @default.
- W3025128826 cites W2912990735 @default.
- W3025128826 cites W2913778552 @default.
- W3025128826 cites W2928252518 @default.
- W3025128826 cites W2931956500 @default.
- W3025128826 cites W2955697347 @default.
- W3025128826 cites W2963173190 @default.
- W3025128826 cites W2963838962 @default.
- W3025128826 cites W2963892472 @default.
- W3025128826 cites W2965497096 @default.
- W3025128826 cites W2970102931 @default.
- W3025128826 cites W2970948008 @default.
- W3025128826 cites W2973033982 @default.
- W3025128826 cites W2994411342 @default.
- W3025128826 cites W3014214117 @default.
- W3025128826 cites W3036237438 @default.
- W3025128826 cites W3081435649 @default.
- W3025128826 cites W3099880660 @default.
- W3025128826 cites W3122451732 @default.
- W3025128826 cites W3128243680 @default.
- W3025128826 cites W3148388528 @default.
- W3025128826 doi "https://doi.org/10.1109/tsp.2021.3102751" @default.
- W3025128826 hasPublicationYear "2021" @default.
- W3025128826 type Work @default.
- W3025128826 sameAs 3025128826 @default.
- W3025128826 citedByCount "0" @default.
- W3025128826 crossrefType "journal-article" @default.
- W3025128826 hasAuthorship W3025128826A5008305849 @default.
- W3025128826 hasAuthorship W3025128826A5010028928 @default.
- W3025128826 hasBestOaLocation W30251288262 @default.
- W3025128826 hasConcept C104317684 @default.
- W3025128826 hasConcept C119857082 @default.
- W3025128826 hasConcept C149782125 @default.
- W3025128826 hasConcept C153180895 @default.
- W3025128826 hasConcept C154945302 @default.
- W3025128826 hasConcept C185592680 @default.
- W3025128826 hasConcept C190470478 @default.
- W3025128826 hasConcept C207609745 @default.
- W3025128826 hasConcept C32834561 @default.
- W3025128826 hasConcept C33923547 @default.
- W3025128826 hasConcept C37914503 @default.
- W3025128826 hasConcept C41008148 @default.
- W3025128826 hasConcept C41608201 @default.
- W3025128826 hasConcept C55493867 @default.
- W3025128826 hasConcept C63479239 @default.