Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962800562> ?p ?o ?g. }
- W2962800562 abstract "Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped based on their correlation so that two groups of strongly and weakly correlated tasks are formed. The two groups of tasks are learned in a curriculum learning setup by transferring the acquired knowledge from the strongly to the weakly correlated. The learning process within each group though, is performed in a multitask classification setup. The proposed method learns better and converges faster than learning all the tasks in a typical multi-task learning paradigm. We demonstrate the effectiveness of our approach on the publicly available, SoBiR, VIPeR and PETA datasets and report state-of-the-art results across the board." @default.
- W2962800562 created "2019-07-30" @default.
- W2962800562 creator A5051145236 @default.
- W2962800562 creator A5058318737 @default.
- W2962800562 creator A5069190127 @default.
- W2962800562 creator A5069699619 @default.
- W2962800562 date "2017-10-01" @default.
- W2962800562 modified "2023-09-30" @default.
- W2962800562 title "Curriculum Learning for Multi-task Classification of Visual Attributes" @default.
- W2962800562 cites W1522973599 @default.
- W2962800562 cites W1924762813 @default.
- W2962800562 cites W2004331293 @default.
- W2962800562 cites W2018006179 @default.
- W2962800562 cites W2040171755 @default.
- W2962800562 cites W2067562626 @default.
- W2962800562 cites W2111025459 @default.
- W2962800562 cites W2117539524 @default.
- W2962800562 cites W2126448884 @default.
- W2962800562 cites W2126942721 @default.
- W2962800562 cites W2128560777 @default.
- W2962800562 cites W2147414309 @default.
- W2962800562 cites W2194775991 @default.
- W2962800562 cites W2296073425 @default.
- W2962800562 cites W2302617085 @default.
- W2962800562 cites W2440214111 @default.
- W2962800562 cites W2473618152 @default.
- W2962800562 cites W2510843126 @default.
- W2962800562 cites W2513699553 @default.
- W2962800562 cites W2518918709 @default.
- W2962800562 cites W2543031684 @default.
- W2962800562 cites W2962860144 @default.
- W2962800562 cites W326271615 @default.
- W2962800562 cites W2591719620 @default.
- W2962800562 doi "https://doi.org/10.1109/iccvw.2017.306" @default.
- W2962800562 hasPublicationYear "2017" @default.
- W2962800562 type Work @default.
- W2962800562 sameAs 2962800562 @default.
- W2962800562 citedByCount "33" @default.
- W2962800562 countsByYear W29628005622018 @default.
- W2962800562 countsByYear W29628005622019 @default.
- W2962800562 countsByYear W29628005622020 @default.
- W2962800562 countsByYear W29628005622021 @default.
- W2962800562 countsByYear W29628005622022 @default.
- W2962800562 countsByYear W29628005622023 @default.
- W2962800562 crossrefType "proceedings-article" @default.
- W2962800562 hasAuthorship W2962800562A5051145236 @default.
- W2962800562 hasAuthorship W2962800562A5058318737 @default.
- W2962800562 hasAuthorship W2962800562A5069190127 @default.
- W2962800562 hasAuthorship W2962800562A5069699619 @default.
- W2962800562 hasBestOaLocation W29628005622 @default.
- W2962800562 hasConcept C107457646 @default.
- W2962800562 hasConcept C111919701 @default.
- W2962800562 hasConcept C116834253 @default.
- W2962800562 hasConcept C119857082 @default.
- W2962800562 hasConcept C127413603 @default.
- W2962800562 hasConcept C154945302 @default.
- W2962800562 hasConcept C15744967 @default.
- W2962800562 hasConcept C184297639 @default.
- W2962800562 hasConcept C19417346 @default.
- W2962800562 hasConcept C201995342 @default.
- W2962800562 hasConcept C2780451532 @default.
- W2962800562 hasConcept C28006648 @default.
- W2962800562 hasConcept C41008148 @default.
- W2962800562 hasConcept C47177190 @default.
- W2962800562 hasConcept C59822182 @default.
- W2962800562 hasConcept C86803240 @default.
- W2962800562 hasConcept C98045186 @default.
- W2962800562 hasConceptScore W2962800562C107457646 @default.
- W2962800562 hasConceptScore W2962800562C111919701 @default.
- W2962800562 hasConceptScore W2962800562C116834253 @default.
- W2962800562 hasConceptScore W2962800562C119857082 @default.
- W2962800562 hasConceptScore W2962800562C127413603 @default.
- W2962800562 hasConceptScore W2962800562C154945302 @default.
- W2962800562 hasConceptScore W2962800562C15744967 @default.
- W2962800562 hasConceptScore W2962800562C184297639 @default.
- W2962800562 hasConceptScore W2962800562C19417346 @default.
- W2962800562 hasConceptScore W2962800562C201995342 @default.
- W2962800562 hasConceptScore W2962800562C2780451532 @default.
- W2962800562 hasConceptScore W2962800562C28006648 @default.
- W2962800562 hasConceptScore W2962800562C41008148 @default.
- W2962800562 hasConceptScore W2962800562C47177190 @default.
- W2962800562 hasConceptScore W2962800562C59822182 @default.
- W2962800562 hasConceptScore W2962800562C86803240 @default.
- W2962800562 hasConceptScore W2962800562C98045186 @default.
- W2962800562 hasLocation W29628005621 @default.
- W2962800562 hasLocation W29628005622 @default.
- W2962800562 hasOpenAccess W2962800562 @default.
- W2962800562 hasPrimaryLocation W29628005621 @default.
- W2962800562 hasRelatedWork W1812322370 @default.
- W2962800562 hasRelatedWork W2597787948 @default.
- W2962800562 hasRelatedWork W2761417937 @default.
- W2962800562 hasRelatedWork W2784094750 @default.
- W2962800562 hasRelatedWork W2961085424 @default.
- W2962800562 hasRelatedWork W3047894882 @default.
- W2962800562 hasRelatedWork W3200098538 @default.
- W2962800562 hasRelatedWork W4285160008 @default.
- W2962800562 hasRelatedWork W4319309271 @default.
- W2962800562 hasRelatedWork W4366320140 @default.
- W2962800562 isParatext "false" @default.
- W2962800562 isRetracted "false" @default.