FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996627958> ?p ?o ?g. }

• W2996627958 abstract "Author(s): Yuan, Tao | Advisor(s): Zhu, Song-Chun | Abstract: Humans can extract rich information from visual scenes, such as the 3D locations of objects and humans, the actions of humans, the states of objects, the belief of humans. Although various state-of-the-art algorithms can achieve good results for solving individual tasks, building a system to jointly infer these different tasks for scene understanding is still an underexplored area. Most of these tasks are not independent with each other, and humans can jointly infer hidden information with their commonsense knowledge among these tasks. In this dissertation, we propose a spatio-temporal framework to jointly infer and optimize multiple tasks across different times and views with a unified explicit probabilistic graphical representation.This dissertation contains four main parts. 1) we describe the system overview, the data flow in the system, and engineering efforts to make the system scalable under different scenarios. 2) we propose an algorithm for holistic 3D scene parsing and human pose estimation with human-object interaction and physical commonsense. Human-object interaction can model the fine-grained relations between agents and objects, and physical commonsense can model the physical plausibility of the reconstructed scene. 3) we introduce a joint parsing framework that integrates view-centric proposals into scene-centric parse graphs that represent a coherent scene-centric understanding of cross-view scenes. 4) we present a joint inference algorithm to understanding object states, robot knowledge, and human beliefs under multi-view settings by maintaining three types of parse graphs. The algorithm can be applied to the cross-view small object tracking problem and some false-belief problems. Experiments show that our joint inference framework can achieve better results than individual algorithms." @default.
• W2996627958 created "2019-12-26" @default.
• W2996627958 creator A5076709596 @default.
• W2996627958 date "2019-01-01" @default.
• W2996627958 modified "2023-09-24" @default.
• W2996627958 title "A Cognition Platform for Joint Inference of 3D Geometry, Object States, and Human Belief" @default.
• W2996627958 hasPublicationYear "2019" @default.
• W2996627958 type Work @default.
• W2996627958 sameAs 2996627958 @default.
• W2996627958 citedByCount "0" @default.
• W2996627958 crossrefType "journal-article" @default.
• W2996627958 hasAuthorship W2996627958A5076709596 @default.
• W2996627958 hasConcept C107457646 @default.
• W2996627958 hasConcept C154945302 @default.
• W2996627958 hasConcept C155846161 @default.
• W2996627958 hasConcept C17744445 @default.
• W2996627958 hasConcept C186644900 @default.
• W2996627958 hasConcept C193221554 @default.
• W2996627958 hasConcept C199539241 @default.
• W2996627958 hasConcept C2776214188 @default.
• W2996627958 hasConcept C2776359362 @default.
• W2996627958 hasConcept C2781238097 @default.
• W2996627958 hasConcept C41008148 @default.
• W2996627958 hasConcept C49937458 @default.
• W2996627958 hasConcept C90509273 @default.
• W2996627958 hasConcept C94625758 @default.
• W2996627958 hasConceptScore W2996627958C107457646 @default.
• W2996627958 hasConceptScore W2996627958C154945302 @default.
• W2996627958 hasConceptScore W2996627958C155846161 @default.
• W2996627958 hasConceptScore W2996627958C17744445 @default.
• W2996627958 hasConceptScore W2996627958C186644900 @default.
• W2996627958 hasConceptScore W2996627958C193221554 @default.
• W2996627958 hasConceptScore W2996627958C199539241 @default.
• W2996627958 hasConceptScore W2996627958C2776214188 @default.
• W2996627958 hasConceptScore W2996627958C2776359362 @default.
• W2996627958 hasConceptScore W2996627958C2781238097 @default.
• W2996627958 hasConceptScore W2996627958C41008148 @default.
• W2996627958 hasConceptScore W2996627958C49937458 @default.
• W2996627958 hasConceptScore W2996627958C90509273 @default.
• W2996627958 hasConceptScore W2996627958C94625758 @default.
• W2996627958 hasLocation W29966279581 @default.
• W2996627958 hasOpenAccess W2996627958 @default.
• W2996627958 hasPrimaryLocation W29966279581 @default.
• W2996627958 hasRelatedWork W2061059350 @default.
• W2996627958 hasRelatedWork W2293760697 @default.
• W2996627958 hasRelatedWork W2581528920 @default.
• W2996627958 hasRelatedWork W2765659515 @default.
• W2996627958 hasRelatedWork W2765772491 @default.
• W2996627958 hasRelatedWork W2788461656 @default.
• W2996627958 hasRelatedWork W2896155353 @default.
• W2996627958 hasRelatedWork W2949015929 @default.
• W2996627958 hasRelatedWork W2961334035 @default.
• W2996627958 hasRelatedWork W2963494435 @default.
• W2996627958 hasRelatedWork W2972165073 @default.
• W2996627958 hasRelatedWork W2994374529 @default.
• W2996627958 hasRelatedWork W3006140463 @default.
• W2996627958 hasRelatedWork W3099059139 @default.
• W2996627958 hasRelatedWork W3129596473 @default.
• W2996627958 hasRelatedWork W3178489527 @default.
• W2996627958 hasRelatedWork W3212054734 @default.
• W2996627958 hasRelatedWork W3213163682 @default.
• W2996627958 hasRelatedWork W126338593 @default.
• W2996627958 hasRelatedWork W1933905718 @default.
• W2996627958 isParatext "false" @default.
• W2996627958 isRetracted "false" @default.
• W2996627958 magId "2996627958" @default.
• W2996627958 workType "article" @default.