FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3164354101> ?p ?o ?g. }

• W3164354101 endingPage "1" @default.
• W3164354101 startingPage "1" @default.
• W3164354101 abstract "Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assumption of knowing which unseen compositions will be available at test time. In this work, we overcome this assumption operating on the open world setting, where no limit is imposed on the compositional space at test time, and the search space contains a large number of unseen compositions. To address this problem, we propose a new approach, Compositional Cosine Graph Embedding (Co-CGE), based on two principles. First, Co-CGE models the dependency between states, objects and their compositions through a graph convolutional neural network. The graph propagates information from seen to unseen concepts, improving their representations. Second, since not all unseen compositions are equally feasible, and less feasible ones may damage the learned representations, Co-CGE estimates a feasibility score for each unseen composition, using the scores as margins in a cosine similarity-based loss and as weights in the adjacency matrix of the graphs. Experiments show that our approach achieves state-of-the-art performances in standard CZSL while outperforming previous methods in the open world scenario." @default.
• W3164354101 created "2021-06-07" @default.
• W3164354101 creator A5012209802 @default.
• W3164354101 creator A5017971549 @default.
• W3164354101 creator A5040372929 @default.
• W3164354101 creator A5061284177 @default.
• W3164354101 date "2022-01-01" @default.
• W3164354101 modified "2023-09-25" @default.
• W3164354101 title "Learning Graph Embeddings for Open World Compositional Zero-Shot Learning" @default.
• W3164354101 cites W1499991161 @default.
• W3164354101 cites W1501418839 @default.
• W3164354101 cites W1522301498 @default.
• W3164354101 cites W1665214252 @default.
• W3164354101 cites W1849277567 @default.
• W3164354101 cites W1948251820 @default.
• W3164354101 cites W2016089260 @default.
• W3164354101 cites W2052293776 @default.
• W3164354101 cites W2077069816 @default.
• W3164354101 cites W2093848332 @default.
• W3164354101 cites W2095705004 @default.
• W3164354101 cites W2102381086 @default.
• W3164354101 cites W2108598243 @default.
• W3164354101 cites W2124033848 @default.
• W3164354101 cites W2128532956 @default.
• W3164354101 cites W2147800946 @default.
• W3164354101 cites W2153579005 @default.
• W3164354101 cites W2156406284 @default.
• W3164354101 cites W2160160833 @default.
• W3164354101 cites W2398118205 @default.
• W3164354101 cites W2400717490 @default.
• W3164354101 cites W2479423890 @default.
• W3164354101 cites W2493916176 @default.
• W3164354101 cites W2552383788 @default.
• W3164354101 cites W2607855566 @default.
• W3164354101 cites W2736809457 @default.
• W3164354101 cites W2753160622 @default.
• W3164354101 cites W2798836702 @default.
• W3164354101 cites W2799029629 @default.
• W3164354101 cites W2799215068 @default.
• W3164354101 cites W2804057010 @default.
• W3164354101 cites W2889167066 @default.
• W3164354101 cites W2913340405 @default.
• W3164354101 cites W2916106175 @default.
• W3164354101 cites W2924485953 @default.
• W3164354101 cites W2936497627 @default.
• W3164354101 cites W2948734064 @default.
• W3164354101 cites W2949945331 @default.
• W3164354101 cites W2950276680 @default.
• W3164354101 cites W2951398059 @default.
• W3164354101 cites W2953271441 @default.
• W3164354101 cites W2963078860 @default.
• W3164354101 cites W2963325024 @default.
• W3164354101 cites W2963486920 @default.
• W3164354101 cites W2963499153 @default.
• W3164354101 cites W2963518342 @default.
• W3164354101 cites W2963814162 @default.
• W3164354101 cites W2963960318 @default.
• W3164354101 cites W2964015378 @default.
• W3164354101 cites W2964051675 @default.
• W3164354101 cites W2967573789 @default.
• W3164354101 cites W2968397098 @default.
• W3164354101 cites W2970843311 @default.
• W3164354101 cites W2970971581 @default.
• W3164354101 cites W2996268457 @default.
• W3164354101 cites W3014002215 @default.
• W3164354101 cites W3034492151 @default.
• W3164354101 cites W3034862692 @default.
• W3164354101 cites W3035084814 @default.
• W3164354101 cites W3103562459 @default.
• W3164354101 cites W3158711590 @default.
• W3164354101 cites W3162332195 @default.
• W3164354101 cites W64813323 @default.
• W3164354101 cites W14333344 @default.
• W3164354101 doi "https://doi.org/10.1109/tpami.2022.3163667" @default.
• W3164354101 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35353693" @default.
• W3164354101 hasPublicationYear "2022" @default.
• W3164354101 type Work @default.
• W3164354101 sameAs 3164354101 @default.
• W3164354101 citedByCount "7" @default.
• W3164354101 countsByYear W31643541012022 @default.
• W3164354101 countsByYear W31643541012023 @default.
• W3164354101 crossrefType "journal-article" @default.
• W3164354101 hasAuthorship W3164354101A5012209802 @default.
• W3164354101 hasAuthorship W3164354101A5017971549 @default.
• W3164354101 hasAuthorship W3164354101A5040372929 @default.
• W3164354101 hasAuthorship W3164354101A5061284177 @default.
• W3164354101 hasBestOaLocation W31643541012 @default.
• W3164354101 hasConcept C110484373 @default.
• W3164354101 hasConcept C11413529 @default.
• W3164354101 hasConcept C119857082 @default.
• W3164354101 hasConcept C132525143 @default.
• W3164354101 hasConcept C153180895 @default.
• W3164354101 hasConcept C154945302 @default.
• W3164354101 hasConcept C180356752 @default.
• W3164354101 hasConcept C2780762811 @default.
• W3164354101 hasConcept C41008148 @default.
• W3164354101 hasConcept C41608201 @default.
• W3164354101 hasConcept C80444323 @default.

• next