Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387323888> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4387323888 abstract "Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer interaction, and video content analysis. This study describes a novel method, integrating graph based modeling with layered hierarchical attention mechanisms, resulting in higher precision and better comprehensiveness of video descriptions. To achieve this, we encode, first, the spatio-temporal inter dependencies between objects and actions with scene graphs and we combine this, in a second step, with a novel 3-level architecture creating a hierarchical attention mechanism using Graph Attention Networks (GATs). The 3-level GAT architecture allows recognizing local, but also global contextual elements. This way several descriptions with different semantic complexity can be generated in parallel for the same video clip, enhancing the discriminative accuracy of action recognition and action description. The performance of our approach is empirically tested using several 2D and 3D datasets. By comparing our method to the state of the art we consistently obtain better performance concerning accuracy, precision, and contextual relevance when evaluating action recognition as well as description generation. In a large set of ablation experiments we also assess the role of the different components of our model. With our multi-level approach the system obtains different semantic description depths, often observed in descriptions made by different people, too. Furthermore, better insight into bimanual hand-object interactions as achieved by our model may portend advancements in the field of robotics, enabling the emulation of intricate human actions with heightened precision." @default.
- W4387323888 created "2023-10-04" @default.
- W4387323888 creator A5015201403 @default.
- W4387323888 creator A5023811677 @default.
- W4387323888 creator A5026724617 @default.
- W4387323888 creator A5043747222 @default.
- W4387323888 creator A5089770964 @default.
- W4387323888 date "2023-10-01" @default.
- W4387323888 modified "2023-10-14" @default.
- W4387323888 title "A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos" @default.
- W4387323888 doi "https://doi.org/10.48550/arxiv.2310.00670" @default.
- W4387323888 hasPublicationYear "2023" @default.
- W4387323888 type Work @default.
- W4387323888 citedByCount "0" @default.
- W4387323888 crossrefType "posted-content" @default.
- W4387323888 hasAuthorship W4387323888A5015201403 @default.
- W4387323888 hasAuthorship W4387323888A5023811677 @default.
- W4387323888 hasAuthorship W4387323888A5026724617 @default.
- W4387323888 hasAuthorship W4387323888A5043747222 @default.
- W4387323888 hasAuthorship W4387323888A5089770964 @default.
- W4387323888 hasBestOaLocation W43873238881 @default.
- W4387323888 hasConcept C101468663 @default.
- W4387323888 hasConcept C104317684 @default.
- W4387323888 hasConcept C107457646 @default.
- W4387323888 hasConcept C111151474 @default.
- W4387323888 hasConcept C111919701 @default.
- W4387323888 hasConcept C119857082 @default.
- W4387323888 hasConcept C132525143 @default.
- W4387323888 hasConcept C149810388 @default.
- W4387323888 hasConcept C154945302 @default.
- W4387323888 hasConcept C162324750 @default.
- W4387323888 hasConcept C185592680 @default.
- W4387323888 hasConcept C2777212361 @default.
- W4387323888 hasConcept C2987834672 @default.
- W4387323888 hasConcept C34413123 @default.
- W4387323888 hasConcept C41008148 @default.
- W4387323888 hasConcept C50522688 @default.
- W4387323888 hasConcept C55493867 @default.
- W4387323888 hasConcept C60692881 @default.
- W4387323888 hasConcept C66746571 @default.
- W4387323888 hasConcept C80444323 @default.
- W4387323888 hasConcept C90509273 @default.
- W4387323888 hasConcept C97931131 @default.
- W4387323888 hasConceptScore W4387323888C101468663 @default.
- W4387323888 hasConceptScore W4387323888C104317684 @default.
- W4387323888 hasConceptScore W4387323888C107457646 @default.
- W4387323888 hasConceptScore W4387323888C111151474 @default.
- W4387323888 hasConceptScore W4387323888C111919701 @default.
- W4387323888 hasConceptScore W4387323888C119857082 @default.
- W4387323888 hasConceptScore W4387323888C132525143 @default.
- W4387323888 hasConceptScore W4387323888C149810388 @default.
- W4387323888 hasConceptScore W4387323888C154945302 @default.
- W4387323888 hasConceptScore W4387323888C162324750 @default.
- W4387323888 hasConceptScore W4387323888C185592680 @default.
- W4387323888 hasConceptScore W4387323888C2777212361 @default.
- W4387323888 hasConceptScore W4387323888C2987834672 @default.
- W4387323888 hasConceptScore W4387323888C34413123 @default.
- W4387323888 hasConceptScore W4387323888C41008148 @default.
- W4387323888 hasConceptScore W4387323888C50522688 @default.
- W4387323888 hasConceptScore W4387323888C55493867 @default.
- W4387323888 hasConceptScore W4387323888C60692881 @default.
- W4387323888 hasConceptScore W4387323888C66746571 @default.
- W4387323888 hasConceptScore W4387323888C80444323 @default.
- W4387323888 hasConceptScore W4387323888C90509273 @default.
- W4387323888 hasConceptScore W4387323888C97931131 @default.
- W4387323888 hasLocation W43873238881 @default.
- W4387323888 hasOpenAccess W4387323888 @default.
- W4387323888 hasPrimaryLocation W43873238881 @default.
- W4387323888 hasRelatedWork W2104731576 @default.
- W4387323888 hasRelatedWork W2113009376 @default.
- W4387323888 hasRelatedWork W2182112479 @default.
- W4387323888 hasRelatedWork W2905846897 @default.
- W4387323888 hasRelatedWork W2965221775 @default.
- W4387323888 hasRelatedWork W2995796742 @default.
- W4387323888 hasRelatedWork W3164403561 @default.
- W4387323888 hasRelatedWork W3191441354 @default.
- W4387323888 hasRelatedWork W4288019231 @default.
- W4387323888 hasRelatedWork W4317655900 @default.
- W4387323888 isParatext "false" @default.
- W4387323888 isRetracted "false" @default.
- W4387323888 workType "article" @default.