Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892664578> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2892664578 endingPage "205" @default.
- W2892664578 startingPage "195" @default.
- W2892664578 abstract "Multi-person activity recognition is a challenging task due to its elusive interactions in activities. We take into account these interactions at two levels. At the individual level, each person behaves depending on both its spatio-temporal features and interactions propagated from others in the scene. At the scene level, the multi-person activity is characterized by interactions between individuals’ actions and the high-level activity. It is worth noting that interactions contribute unequally at both levels. To jointly explore these colorful interactions, we propose a two-level attention-based interaction model relying on two time-varying attention mechanisms. The individual-level attention mechanism conditioned on pose features, exploits various degrees of interactions among individuals in a scene while updating their states at each time step. The scene-level attention mechanism proposes an attention-based pooling strategy to explore various levels of interactions between individuals’ actions and the high-level activity. We ground our model by a modified two-stage Gated Recurrent Units (GRUs) network to handle the long-range temporal variability and consistency. Our end-to-end trainable model takes as inputs a set of person detections in videos or image sequences and predicts labels of multi-person activities. Experimental results demonstrate comparable performance of our model and show the effectiveness of our attention mechanisms." @default.
- W2892664578 created "2018-10-05" @default.
- W2892664578 creator A5006776719 @default.
- W2892664578 creator A5021541475 @default.
- W2892664578 creator A5050398532 @default.
- W2892664578 creator A5066474034 @default.
- W2892664578 creator A5070779003 @default.
- W2892664578 date "2018-12-01" @default.
- W2892664578 modified "2023-09-22" @default.
- W2892664578 title "A two-level attention-based interaction model for multi-person activity recognition" @default.
- W2892664578 cites W1973326669 @default.
- W2892664578 cites W2003708924 @default.
- W2892664578 cites W2047499569 @default.
- W2892664578 cites W2157200118 @default.
- W2892664578 cites W2224196924 @default.
- W2892664578 cites W2550155684 @default.
- W2892664578 cites W2622398900 @default.
- W2892664578 cites W2733137411 @default.
- W2892664578 doi "https://doi.org/10.1016/j.neucom.2018.09.060" @default.
- W2892664578 hasPublicationYear "2018" @default.
- W2892664578 type Work @default.
- W2892664578 sameAs 2892664578 @default.
- W2892664578 citedByCount "13" @default.
- W2892664578 countsByYear W28926645782019 @default.
- W2892664578 countsByYear W28926645782020 @default.
- W2892664578 countsByYear W28926645782021 @default.
- W2892664578 countsByYear W28926645782022 @default.
- W2892664578 countsByYear W28926645782023 @default.
- W2892664578 crossrefType "journal-article" @default.
- W2892664578 hasAuthorship W2892664578A5006776719 @default.
- W2892664578 hasAuthorship W2892664578A5021541475 @default.
- W2892664578 hasAuthorship W2892664578A5050398532 @default.
- W2892664578 hasAuthorship W2892664578A5066474034 @default.
- W2892664578 hasAuthorship W2892664578A5070779003 @default.
- W2892664578 hasConcept C119857082 @default.
- W2892664578 hasConcept C121687571 @default.
- W2892664578 hasConcept C154945302 @default.
- W2892664578 hasConcept C162324750 @default.
- W2892664578 hasConcept C177264268 @default.
- W2892664578 hasConcept C187736073 @default.
- W2892664578 hasConcept C199360897 @default.
- W2892664578 hasConcept C2776436953 @default.
- W2892664578 hasConcept C2780451532 @default.
- W2892664578 hasConcept C41008148 @default.
- W2892664578 hasConcept C70437156 @default.
- W2892664578 hasConceptScore W2892664578C119857082 @default.
- W2892664578 hasConceptScore W2892664578C121687571 @default.
- W2892664578 hasConceptScore W2892664578C154945302 @default.
- W2892664578 hasConceptScore W2892664578C162324750 @default.
- W2892664578 hasConceptScore W2892664578C177264268 @default.
- W2892664578 hasConceptScore W2892664578C187736073 @default.
- W2892664578 hasConceptScore W2892664578C199360897 @default.
- W2892664578 hasConceptScore W2892664578C2776436953 @default.
- W2892664578 hasConceptScore W2892664578C2780451532 @default.
- W2892664578 hasConceptScore W2892664578C41008148 @default.
- W2892664578 hasConceptScore W2892664578C70437156 @default.
- W2892664578 hasFunder F4320321001 @default.
- W2892664578 hasLocation W28926645781 @default.
- W2892664578 hasOpenAccess W2892664578 @default.
- W2892664578 hasPrimaryLocation W28926645781 @default.
- W2892664578 hasRelatedWork W1509083187 @default.
- W2892664578 hasRelatedWork W2558383949 @default.
- W2892664578 hasRelatedWork W3011192796 @default.
- W2892664578 hasRelatedWork W3036630077 @default.
- W2892664578 hasRelatedWork W3093454656 @default.
- W2892664578 hasRelatedWork W3135542633 @default.
- W2892664578 hasRelatedWork W4249229055 @default.
- W2892664578 hasRelatedWork W4281386417 @default.
- W2892664578 hasRelatedWork W4323546569 @default.
- W2892664578 hasRelatedWork W4377699614 @default.
- W2892664578 hasVolume "322" @default.
- W2892664578 isParatext "false" @default.
- W2892664578 isRetracted "false" @default.
- W2892664578 magId "2892664578" @default.
- W2892664578 workType "article" @default.