Matches in SemOpenAlex for { <https://semopenalex.org/work/W2998178630> ?p ?o ?g. }
- W2998178630 abstract "We propose a new method for anomaly detection of human actions. Our method works directly on human pose graphs that can be computed from an input video sequence. This makes the analysis independent of nuisance parameters such as viewpoint or illumination. We map these graphs to a latent space and cluster them. Each action is then represented by its soft-assignment to each of the clusters. This gives a kind of bag of words representation to the data, where every action is represented by its similarity to a group of base action-words. Then, we use a Dirichlet process based mixture, that is useful for handling proportional data such as our soft-assignment vectors, to determine if an action is normal or not. We evaluate our method on two types of data sets. The first is a fine-grained anomaly detection data set (e.g. ShanghaiTech) where we wish to detect unusual variations of some action. The second is a coarse-grained anomaly detection data set (e.g., a Kinetics-based data set) where few actions are considered normal, and every other action should be considered abnormal. Extensive experiments on the benchmarks show that our method performs considerably better than other state of the art methods." @default.
- W2998178630 created "2020-01-10" @default.
- W2998178630 creator A5039715608 @default.
- W2998178630 creator A5051411799 @default.
- W2998178630 creator A5068635313 @default.
- W2998178630 creator A5069943381 @default.
- W2998178630 creator A5086469528 @default.
- W2998178630 date "2019-12-26" @default.
- W2998178630 modified "2023-09-27" @default.
- W2998178630 title "Graph Embedded Pose Clustering for Anomaly Detection" @default.
- W2998178630 cites W1531367268 @default.
- W2998178630 cites W1902237438 @default.
- W2998178630 cites W2027721066 @default.
- W2998178630 cites W2127498532 @default.
- W2998178630 cites W2175711684 @default.
- W2998178630 cites W2341058432 @default.
- W2998178630 cites W2559085405 @default.
- W2998178630 cites W2559927751 @default.
- W2998178630 cites W2579718262 @default.
- W2998178630 cites W2587789887 @default.
- W2998178630 cites W2608862709 @default.
- W2998178630 cites W2613718673 @default.
- W2998178630 cites W2619947201 @default.
- W2998178630 cites W2753526808 @default.
- W2998178630 cites W2766042539 @default.
- W2998178630 cites W2777342313 @default.
- W2998178630 cites W2788552663 @default.
- W2998178630 cites W2883725317 @default.
- W2998178630 cites W2911672077 @default.
- W2998178630 cites W2921906393 @default.
- W2998178630 cites W2925312408 @default.
- W2998178630 cites W2955007221 @default.
- W2998178630 cites W2963076818 @default.
- W2998178630 cites W2963403868 @default.
- W2998178630 cites W2963610939 @default.
- W2998178630 cites W2963708869 @default.
- W2998178630 cites W2963781481 @default.
- W2998178630 cites W2964010455 @default.
- W2998178630 cites W2964015378 @default.
- W2998178630 cites W2964074409 @default.
- W2998178630 cites W2964121744 @default.
- W2998178630 cites W2964134613 @default.
- W2998178630 cites W2964232409 @default.
- W2998178630 cites W3103720336 @default.
- W2998178630 cites W3153872861 @default.
- W2998178630 hasPublicationYear "2019" @default.
- W2998178630 type Work @default.
- W2998178630 sameAs 2998178630 @default.
- W2998178630 citedByCount "0" @default.
- W2998178630 crossrefType "posted-content" @default.
- W2998178630 hasAuthorship W2998178630A5039715608 @default.
- W2998178630 hasAuthorship W2998178630A5051411799 @default.
- W2998178630 hasAuthorship W2998178630A5068635313 @default.
- W2998178630 hasAuthorship W2998178630A5069943381 @default.
- W2998178630 hasAuthorship W2998178630A5086469528 @default.
- W2998178630 hasConcept C121332964 @default.
- W2998178630 hasConcept C124101348 @default.
- W2998178630 hasConcept C13672336 @default.
- W2998178630 hasConcept C153180895 @default.
- W2998178630 hasConcept C154945302 @default.
- W2998178630 hasConcept C177264268 @default.
- W2998178630 hasConcept C17744445 @default.
- W2998178630 hasConcept C199360897 @default.
- W2998178630 hasConcept C199539241 @default.
- W2998178630 hasConcept C2776359362 @default.
- W2998178630 hasConcept C2780791683 @default.
- W2998178630 hasConcept C41008148 @default.
- W2998178630 hasConcept C62520636 @default.
- W2998178630 hasConcept C73555534 @default.
- W2998178630 hasConcept C739882 @default.
- W2998178630 hasConcept C94625758 @default.
- W2998178630 hasConceptScore W2998178630C121332964 @default.
- W2998178630 hasConceptScore W2998178630C124101348 @default.
- W2998178630 hasConceptScore W2998178630C13672336 @default.
- W2998178630 hasConceptScore W2998178630C153180895 @default.
- W2998178630 hasConceptScore W2998178630C154945302 @default.
- W2998178630 hasConceptScore W2998178630C177264268 @default.
- W2998178630 hasConceptScore W2998178630C17744445 @default.
- W2998178630 hasConceptScore W2998178630C199360897 @default.
- W2998178630 hasConceptScore W2998178630C199539241 @default.
- W2998178630 hasConceptScore W2998178630C2776359362 @default.
- W2998178630 hasConceptScore W2998178630C2780791683 @default.
- W2998178630 hasConceptScore W2998178630C41008148 @default.
- W2998178630 hasConceptScore W2998178630C62520636 @default.
- W2998178630 hasConceptScore W2998178630C73555534 @default.
- W2998178630 hasConceptScore W2998178630C739882 @default.
- W2998178630 hasConceptScore W2998178630C94625758 @default.
- W2998178630 hasLocation W29981786301 @default.
- W2998178630 hasOpenAccess W2998178630 @default.
- W2998178630 hasPrimaryLocation W29981786301 @default.
- W2998178630 hasRelatedWork W1532610764 @default.
- W2998178630 hasRelatedWork W1898102941 @default.
- W2998178630 hasRelatedWork W1969964242 @default.
- W2998178630 hasRelatedWork W199156503 @default.
- W2998178630 hasRelatedWork W2080506076 @default.
- W2998178630 hasRelatedWork W2379047778 @default.
- W2998178630 hasRelatedWork W2398278670 @default.
- W2998178630 hasRelatedWork W2406810007 @default.
- W2998178630 hasRelatedWork W2498678855 @default.
- W2998178630 hasRelatedWork W2578504632 @default.