Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211779> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4387211779 endingPage "311" @default.
- W4387211779 startingPage "302" @default.
- W4387211779 abstract "Modern surgeries are performed in complex and dynamic settings, including ever-changing interactions between medical staff, patients, and equipment. The holistic modeling of the operating room (OR) is, therefore, a challenging but essential task, with the potential to optimize the performance of surgical teams and aid in developing new surgical technologies to improve patient outcomes. The holistic representation of surgical scenes as semantic scene graphs (SGG), where entities are represented as nodes and relations between them as edges, is a promising direction for fine-grained semantic OR understanding. We propose, for the first time, the use of temporal information for more accurate and consistent holistic OR modeling. Specifically, we introduce memory scene graphs, where the scene graphs of previous time steps act as the temporal representation guiding the current prediction. We design an end-to-end architecture that intelligently fuses the temporal information of our lightweight memory scene graphs with the visual information from point clouds and images. We evaluate our method on the 4D-OR dataset and demonstrate that integrating temporality leads to more accurate and consistent results achieving an +5% increase and a new SOTA of 0.88 in macro F1. This work opens the path for representing the entire surgery history with memory scene graphs and improves the holistic understanding in the OR. Introducing scene graphs as memory representations can offer a valuable tool for many temporal understanding tasks. We will publish our code upon acceptance. The code is publicly available at https://github.com/egeozsoy/LABRAD-OR ." @default.
- W4387211779 created "2023-10-01" @default.
- W4387211779 creator A5003203833 @default.
- W4387211779 creator A5046896448 @default.
- W4387211779 creator A5056419170 @default.
- W4387211779 creator A5064537879 @default.
- W4387211779 creator A5076794873 @default.
- W4387211779 date "2023-01-01" @default.
- W4387211779 modified "2023-10-13" @default.
- W4387211779 title "LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms" @default.
- W4387211779 cites W2016545368 @default.
- W4387211779 cites W2266464013 @default.
- W4387211779 cites W2579549467 @default.
- W4387211779 cites W2580456502 @default.
- W4387211779 cites W2979797179 @default.
- W4387211779 cites W3034679267 @default.
- W4387211779 cites W3035154952 @default.
- W4387211779 cites W3091895136 @default.
- W4387211779 cites W3092562667 @default.
- W4387211779 cites W3092646344 @default.
- W4387211779 cites W3110266995 @default.
- W4387211779 cites W3127470776 @default.
- W4387211779 cites W3186621246 @default.
- W4387211779 cites W3193902142 @default.
- W4387211779 cites W3198379050 @default.
- W4387211779 cites W3201659970 @default.
- W4387211779 cites W4223545025 @default.
- W4387211779 cites W4284961286 @default.
- W4387211779 cites W4296054450 @default.
- W4387211779 cites W4296195896 @default.
- W4387211779 cites W4321232426 @default.
- W4387211779 cites W4366985998 @default.
- W4387211779 doi "https://doi.org/10.1007/978-3-031-43996-4_29" @default.
- W4387211779 hasPublicationYear "2023" @default.
- W4387211779 type Work @default.
- W4387211779 citedByCount "0" @default.
- W4387211779 crossrefType "book-chapter" @default.
- W4387211779 hasAuthorship W4387211779A5003203833 @default.
- W4387211779 hasAuthorship W4387211779A5046896448 @default.
- W4387211779 hasAuthorship W4387211779A5056419170 @default.
- W4387211779 hasAuthorship W4387211779A5064537879 @default.
- W4387211779 hasAuthorship W4387211779A5076794873 @default.
- W4387211779 hasConcept C107457646 @default.
- W4387211779 hasConcept C111472728 @default.
- W4387211779 hasConcept C138885662 @default.
- W4387211779 hasConcept C141679102 @default.
- W4387211779 hasConcept C154945302 @default.
- W4387211779 hasConcept C162324750 @default.
- W4387211779 hasConcept C166955791 @default.
- W4387211779 hasConcept C177264268 @default.
- W4387211779 hasConcept C17744445 @default.
- W4387211779 hasConcept C187736073 @default.
- W4387211779 hasConcept C199360897 @default.
- W4387211779 hasConcept C199539241 @default.
- W4387211779 hasConcept C2776359362 @default.
- W4387211779 hasConcept C2776760102 @default.
- W4387211779 hasConcept C2777735758 @default.
- W4387211779 hasConcept C2780451532 @default.
- W4387211779 hasConcept C41008148 @default.
- W4387211779 hasConcept C94625758 @default.
- W4387211779 hasConceptScore W4387211779C107457646 @default.
- W4387211779 hasConceptScore W4387211779C111472728 @default.
- W4387211779 hasConceptScore W4387211779C138885662 @default.
- W4387211779 hasConceptScore W4387211779C141679102 @default.
- W4387211779 hasConceptScore W4387211779C154945302 @default.
- W4387211779 hasConceptScore W4387211779C162324750 @default.
- W4387211779 hasConceptScore W4387211779C166955791 @default.
- W4387211779 hasConceptScore W4387211779C177264268 @default.
- W4387211779 hasConceptScore W4387211779C17744445 @default.
- W4387211779 hasConceptScore W4387211779C187736073 @default.
- W4387211779 hasConceptScore W4387211779C199360897 @default.
- W4387211779 hasConceptScore W4387211779C199539241 @default.
- W4387211779 hasConceptScore W4387211779C2776359362 @default.
- W4387211779 hasConceptScore W4387211779C2776760102 @default.
- W4387211779 hasConceptScore W4387211779C2777735758 @default.
- W4387211779 hasConceptScore W4387211779C2780451532 @default.
- W4387211779 hasConceptScore W4387211779C41008148 @default.
- W4387211779 hasConceptScore W4387211779C94625758 @default.
- W4387211779 hasLocation W43872117791 @default.
- W4387211779 hasOpenAccess W4387211779 @default.
- W4387211779 hasPrimaryLocation W43872117791 @default.
- W4387211779 hasRelatedWork W1974811204 @default.
- W4387211779 hasRelatedWork W2071599890 @default.
- W4387211779 hasRelatedWork W2081647779 @default.
- W4387211779 hasRelatedWork W2088072380 @default.
- W4387211779 hasRelatedWork W2174977426 @default.
- W4387211779 hasRelatedWork W2373724792 @default.
- W4387211779 hasRelatedWork W3042714668 @default.
- W4387211779 hasRelatedWork W3128051602 @default.
- W4387211779 hasRelatedWork W4237750775 @default.
- W4387211779 hasRelatedWork W4312391057 @default.
- W4387211779 isParatext "false" @default.
- W4387211779 isRetracted "false" @default.
- W4387211779 workType "book-chapter" @default.