Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366851048> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4366851048 abstract "Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories." @default.
- W4366851048 created "2023-04-25" @default.
- W4366851048 creator A5001498982 @default.
- W4366851048 creator A5006247366 @default.
- W4366851048 creator A5035742417 @default.
- W4366851048 creator A5045117407 @default.
- W4366851048 creator A5047692636 @default.
- W4366851048 creator A5051931459 @default.
- W4366851048 creator A5081893016 @default.
- W4366851048 date "2023-04-21" @default.
- W4366851048 modified "2023-09-25" @default.
- W4366851048 title "Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation" @default.
- W4366851048 doi "https://doi.org/10.48550/arxiv.2304.10773" @default.
- W4366851048 hasPublicationYear "2023" @default.
- W4366851048 type Work @default.
- W4366851048 citedByCount "0" @default.
- W4366851048 crossrefType "posted-content" @default.
- W4366851048 hasAuthorship W4366851048A5001498982 @default.
- W4366851048 hasAuthorship W4366851048A5006247366 @default.
- W4366851048 hasAuthorship W4366851048A5035742417 @default.
- W4366851048 hasAuthorship W4366851048A5045117407 @default.
- W4366851048 hasAuthorship W4366851048A5047692636 @default.
- W4366851048 hasAuthorship W4366851048A5051931459 @default.
- W4366851048 hasAuthorship W4366851048A5081893016 @default.
- W4366851048 hasConcept C107457646 @default.
- W4366851048 hasConcept C134306372 @default.
- W4366851048 hasConcept C142362112 @default.
- W4366851048 hasConcept C153349607 @default.
- W4366851048 hasConcept C154945302 @default.
- W4366851048 hasConcept C162324750 @default.
- W4366851048 hasConcept C177148314 @default.
- W4366851048 hasConcept C17744445 @default.
- W4366851048 hasConcept C187736073 @default.
- W4366851048 hasConcept C199539241 @default.
- W4366851048 hasConcept C2775937380 @default.
- W4366851048 hasConcept C2776359362 @default.
- W4366851048 hasConcept C2780451532 @default.
- W4366851048 hasConcept C33923547 @default.
- W4366851048 hasConcept C41008148 @default.
- W4366851048 hasConcept C90509273 @default.
- W4366851048 hasConcept C94625758 @default.
- W4366851048 hasConceptScore W4366851048C107457646 @default.
- W4366851048 hasConceptScore W4366851048C134306372 @default.
- W4366851048 hasConceptScore W4366851048C142362112 @default.
- W4366851048 hasConceptScore W4366851048C153349607 @default.
- W4366851048 hasConceptScore W4366851048C154945302 @default.
- W4366851048 hasConceptScore W4366851048C162324750 @default.
- W4366851048 hasConceptScore W4366851048C177148314 @default.
- W4366851048 hasConceptScore W4366851048C17744445 @default.
- W4366851048 hasConceptScore W4366851048C187736073 @default.
- W4366851048 hasConceptScore W4366851048C199539241 @default.
- W4366851048 hasConceptScore W4366851048C2775937380 @default.
- W4366851048 hasConceptScore W4366851048C2776359362 @default.
- W4366851048 hasConceptScore W4366851048C2780451532 @default.
- W4366851048 hasConceptScore W4366851048C33923547 @default.
- W4366851048 hasConceptScore W4366851048C41008148 @default.
- W4366851048 hasConceptScore W4366851048C90509273 @default.
- W4366851048 hasConceptScore W4366851048C94625758 @default.
- W4366851048 hasLocation W43668510481 @default.
- W4366851048 hasOpenAccess W4366851048 @default.
- W4366851048 hasPrimaryLocation W43668510481 @default.
- W4366851048 hasRelatedWork W1763389228 @default.
- W4366851048 hasRelatedWork W2079554071 @default.
- W4366851048 hasRelatedWork W2162746924 @default.
- W4366851048 hasRelatedWork W2166791242 @default.
- W4366851048 hasRelatedWork W2323122434 @default.
- W4366851048 hasRelatedWork W2343019076 @default.
- W4366851048 hasRelatedWork W3022671439 @default.
- W4366851048 hasRelatedWork W3038859464 @default.
- W4366851048 hasRelatedWork W3040778547 @default.
- W4366851048 hasRelatedWork W3138568041 @default.
- W4366851048 isParatext "false" @default.
- W4366851048 isRetracted "false" @default.
- W4366851048 workType "article" @default.