Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361763610> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4361763610 endingPage "696" @default.
- W4361763610 startingPage "690" @default.
- W4361763610 abstract "With the tremendous increase in video data size, search performance could be impacted significantly. Specifically, in an interactive system, a real-time system allows a user to browse, search and refine a query. Without a speedy system quickly, the main ingredient to engage a user to stay focused, an interactive system becomes less effective even with a sophisticated deep learning system. This paper addresses this challenge by leveraging approximate search, Bayesian inference, and reinforcement learning. For approximate search, we apply a hierarchical navigable small world, which is an efficient approximate nearest neighbor search algorithm. To quickly prune the search scope, we integrate PicHunter, one of the most popular engines in Video Browser Showdown, with reinforcement learning. The integration enhances PicHunter with the ability of systematic planning. Specifically, PicHunter performs a Bayesian update with a greedy strategy to select a small number of candidates for display. With reinforcement learning, the greedy strategy is replaced with a policy network that learns to select candidates that will result in the minimum number of user iterations, which is analytically defined by a reward function. With these improvements, the interactive system only searches a subset of video datasets relevant to a query while being able to quickly perform Bayesian updates with systematic planning to recommend the most probable candidates that can potentially lead to minimum iteration rounds." @default.
- W4361763610 created "2023-04-04" @default.
- W4361763610 creator A5010722442 @default.
- W4361763610 creator A5023483004 @default.
- W4361763610 creator A5038280962 @default.
- W4361763610 creator A5056908913 @default.
- W4361763610 date "2023-01-01" @default.
- W4361763610 modified "2023-09-27" @default.
- W4361763610 title "Reinforcement Learning Enhanced PicHunter for Interactive Search" @default.
- W4361763610 cites W2155099190 @default.
- W4361763610 cites W2425121537 @default.
- W4361763610 cites W2950557411 @default.
- W4361763610 cites W2963469388 @default.
- W4361763610 cites W2998502625 @default.
- W4361763610 cites W3097514502 @default.
- W4361763610 cites W3183241901 @default.
- W4361763610 cites W4210565368 @default.
- W4361763610 cites W4220683311 @default.
- W4361763610 cites W4283807773 @default.
- W4361763610 cites W4285606530 @default.
- W4361763610 cites W4304099291 @default.
- W4361763610 doi "https://doi.org/10.1007/978-3-031-27077-2_60" @default.
- W4361763610 hasPublicationYear "2023" @default.
- W4361763610 type Work @default.
- W4361763610 citedByCount "0" @default.
- W4361763610 crossrefType "book-chapter" @default.
- W4361763610 hasAuthorship W4361763610A5010722442 @default.
- W4361763610 hasAuthorship W4361763610A5023483004 @default.
- W4361763610 hasAuthorship W4361763610A5038280962 @default.
- W4361763610 hasAuthorship W4361763610A5056908913 @default.
- W4361763610 hasConcept C107673813 @default.
- W4361763610 hasConcept C11413529 @default.
- W4361763610 hasConcept C119857082 @default.
- W4361763610 hasConcept C154945302 @default.
- W4361763610 hasConcept C199360897 @default.
- W4361763610 hasConcept C2778012447 @default.
- W4361763610 hasConcept C2778049539 @default.
- W4361763610 hasConcept C33724603 @default.
- W4361763610 hasConcept C41008148 @default.
- W4361763610 hasConcept C51823790 @default.
- W4361763610 hasConcept C97541855 @default.
- W4361763610 hasConceptScore W4361763610C107673813 @default.
- W4361763610 hasConceptScore W4361763610C11413529 @default.
- W4361763610 hasConceptScore W4361763610C119857082 @default.
- W4361763610 hasConceptScore W4361763610C154945302 @default.
- W4361763610 hasConceptScore W4361763610C199360897 @default.
- W4361763610 hasConceptScore W4361763610C2778012447 @default.
- W4361763610 hasConceptScore W4361763610C2778049539 @default.
- W4361763610 hasConceptScore W4361763610C33724603 @default.
- W4361763610 hasConceptScore W4361763610C41008148 @default.
- W4361763610 hasConceptScore W4361763610C51823790 @default.
- W4361763610 hasConceptScore W4361763610C97541855 @default.
- W4361763610 hasLocation W43617636101 @default.
- W4361763610 hasOpenAccess W4361763610 @default.
- W4361763610 hasPrimaryLocation W43617636101 @default.
- W4361763610 hasRelatedWork W1535019556 @default.
- W4361763610 hasRelatedWork W2780123820 @default.
- W4361763610 hasRelatedWork W2895133117 @default.
- W4361763610 hasRelatedWork W2949274245 @default.
- W4361763610 hasRelatedWork W3022038857 @default.
- W4361763610 hasRelatedWork W3199608561 @default.
- W4361763610 hasRelatedWork W4301965207 @default.
- W4361763610 hasRelatedWork W4319083788 @default.
- W4361763610 hasRelatedWork W4321146100 @default.
- W4361763610 hasRelatedWork W4300772058 @default.
- W4361763610 isParatext "false" @default.
- W4361763610 isRetracted "false" @default.
- W4361763610 workType "book-chapter" @default.