Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288263487> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4288263487 abstract "A classical approach to abnormal activity detection is to learn a representation for normal activities from the training data and then use this learned representation to detect abnormal activities while testing. Typically, the methods based on this approach operate at a fixed timescale - either a single time-instant (eg. frame-based) or a constant time duration (eg. video-clip based). But human abnormal activities can take place at different timescales. For example, jumping is a short term anomaly and loitering is a long term anomaly in a surveillance scenario. A single and pre-defined timescale is not enough to capture the wide range of anomalies occurring with different time duration. In this paper, we propose a multi-timescale model to capture the temporal dynamics at different timescales. In particular, the proposed model makes future and past predictions at different timescales for a given input pose trajectory. The model is multi-layered where intermediate layers are responsible to generate predictions corresponding to different timescales. These predictions are combined to detect abnormal activities. In addition, we also introduce an abnormal activity data-set for research use that contains 4,83,566 annotated frames. Data-set will be made available at https://rodrigues-royston.github.io/Multi-timescale_Trajectory_Prediction/ Our experiments show that the proposed model can capture the anomalies of different time duration and outperforms existing methods." @default.
- W4288263487 created "2022-07-28" @default.
- W4288263487 creator A5016405213 @default.
- W4288263487 creator A5025512806 @default.
- W4288263487 creator A5060996961 @default.
- W4288263487 creator A5075227880 @default.
- W4288263487 date "2019-08-12" @default.
- W4288263487 modified "2023-09-23" @default.
- W4288263487 title "Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection" @default.
- W4288263487 doi "https://doi.org/10.48550/arxiv.1908.04321" @default.
- W4288263487 hasPublicationYear "2019" @default.
- W4288263487 type Work @default.
- W4288263487 citedByCount "0" @default.
- W4288263487 crossrefType "posted-content" @default.
- W4288263487 hasAuthorship W4288263487A5016405213 @default.
- W4288263487 hasAuthorship W4288263487A5025512806 @default.
- W4288263487 hasAuthorship W4288263487A5060996961 @default.
- W4288263487 hasAuthorship W4288263487A5075227880 @default.
- W4288263487 hasBestOaLocation W42882634871 @default.
- W4288263487 hasConcept C112758219 @default.
- W4288263487 hasConcept C121332964 @default.
- W4288263487 hasConcept C124101348 @default.
- W4288263487 hasConcept C126042441 @default.
- W4288263487 hasConcept C127413603 @default.
- W4288263487 hasConcept C1276947 @default.
- W4288263487 hasConcept C12997251 @default.
- W4288263487 hasConcept C13662910 @default.
- W4288263487 hasConcept C146978453 @default.
- W4288263487 hasConcept C154945302 @default.
- W4288263487 hasConcept C177264268 @default.
- W4288263487 hasConcept C17744445 @default.
- W4288263487 hasConcept C199360897 @default.
- W4288263487 hasConcept C199539241 @default.
- W4288263487 hasConcept C204323151 @default.
- W4288263487 hasConcept C24890656 @default.
- W4288263487 hasConcept C26873012 @default.
- W4288263487 hasConcept C2776359362 @default.
- W4288263487 hasConcept C41008148 @default.
- W4288263487 hasConcept C58489278 @default.
- W4288263487 hasConcept C61797465 @default.
- W4288263487 hasConcept C62520636 @default.
- W4288263487 hasConcept C739882 @default.
- W4288263487 hasConcept C76155785 @default.
- W4288263487 hasConcept C94625758 @default.
- W4288263487 hasConceptScore W4288263487C112758219 @default.
- W4288263487 hasConceptScore W4288263487C121332964 @default.
- W4288263487 hasConceptScore W4288263487C124101348 @default.
- W4288263487 hasConceptScore W4288263487C126042441 @default.
- W4288263487 hasConceptScore W4288263487C127413603 @default.
- W4288263487 hasConceptScore W4288263487C1276947 @default.
- W4288263487 hasConceptScore W4288263487C12997251 @default.
- W4288263487 hasConceptScore W4288263487C13662910 @default.
- W4288263487 hasConceptScore W4288263487C146978453 @default.
- W4288263487 hasConceptScore W4288263487C154945302 @default.
- W4288263487 hasConceptScore W4288263487C177264268 @default.
- W4288263487 hasConceptScore W4288263487C17744445 @default.
- W4288263487 hasConceptScore W4288263487C199360897 @default.
- W4288263487 hasConceptScore W4288263487C199539241 @default.
- W4288263487 hasConceptScore W4288263487C204323151 @default.
- W4288263487 hasConceptScore W4288263487C24890656 @default.
- W4288263487 hasConceptScore W4288263487C26873012 @default.
- W4288263487 hasConceptScore W4288263487C2776359362 @default.
- W4288263487 hasConceptScore W4288263487C41008148 @default.
- W4288263487 hasConceptScore W4288263487C58489278 @default.
- W4288263487 hasConceptScore W4288263487C61797465 @default.
- W4288263487 hasConceptScore W4288263487C62520636 @default.
- W4288263487 hasConceptScore W4288263487C739882 @default.
- W4288263487 hasConceptScore W4288263487C76155785 @default.
- W4288263487 hasConceptScore W4288263487C94625758 @default.
- W4288263487 hasLocation W42882634871 @default.
- W4288263487 hasOpenAccess W4288263487 @default.
- W4288263487 hasPrimaryLocation W42882634871 @default.
- W4288263487 hasRelatedWork W1987029079 @default.
- W4288263487 hasRelatedWork W2082233142 @default.
- W4288263487 hasRelatedWork W2372557666 @default.
- W4288263487 hasRelatedWork W2391943197 @default.
- W4288263487 hasRelatedWork W2392397575 @default.
- W4288263487 hasRelatedWork W2510837443 @default.
- W4288263487 hasRelatedWork W2888412392 @default.
- W4288263487 hasRelatedWork W2968202956 @default.
- W4288263487 hasRelatedWork W2993400593 @default.
- W4288263487 hasRelatedWork W4229021642 @default.
- W4288263487 isParatext "false" @default.
- W4288263487 isRetracted "false" @default.
- W4288263487 workType "article" @default.