FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080324> ?p ?o ?g. }

• W4304080324 abstract "Learning spatial and temporal relations among people plays an important role in recognizing group activity. Recently, transformer-based methods have become popular solutions due to the proposal of self-attention mechanism. However, the person-level features are fed directly into the self-attention module without any refinement. Moreover, group activity in a clip often involves unbalanced spatio-temporal interactions, where only a few persons with special actions are critical to identifying different activities. It is difficult to learn the spatio-temporal interactions due to the lack of elaborately modeling the action dependencies among all people. In this paper, a novel Action-guided Spatio-Temporal transFormer (ASTFormer) is proposed to capture the interaction relations for group activity recognition by learning action-centric aggregation and modeling spatio-temporal action dependencies. Specifically, ASTFormer starts with assigning all persons in each frame to the latent actions, while an action-centric aggregation strategy is performed by weighting the sum of residuals for each latent action under the supervision of global action information. Then, a dual-branch transformer is proposed to refine the inter- and intra-frame action-level features, where two encoders with the self-attention mechanism are employed to select important tokens. Next, a semantic action graph is explicitly devised to model the dynamic action-wise dependencies. Finally, our model is capable of boosting group activity recognition by fusing these important cues, while only requiring video-level action labels. Extensive experiments on two popular benchmarks (Volleyball and Collective Activity) demonstrate the superior performance of our method in comparison with the state-of-the-art methods using only raw RGB frames as input." @default.
• W4304080324 created "2022-10-10" @default.
• W4304080324 creator A5000432967 @default.
• W4304080324 creator A5010665898 @default.
• W4304080324 creator A5011680564 @default.
• W4304080324 creator A5019960435 @default.
• W4304080324 creator A5045727713 @default.
• W4304080324 date "2022-10-10" @default.
• W4304080324 modified "2023-10-16" @default.
• W4304080324 title "Learning Action-guided Spatio-temporal Transformer for Group Activity Recognition" @default.
• W4304080324 cites W2000143015 @default.
• W4304080324 cites W2097117768 @default.
• W4304080324 cites W2171544105 @default.
• W4304080324 cites W2194775991 @default.
• W4304080324 cites W2202703817 @default.
• W4304080324 cites W2259801182 @default.
• W4304080324 cites W2269938945 @default.
• W4304080324 cites W2290998037 @default.
• W4304080324 cites W2558630670 @default.
• W4304080324 cites W2608988379 @default.
• W4304080324 cites W2620629206 @default.
• W4304080324 cites W2736442062 @default.
• W4304080324 cites W2778252923 @default.
• W4304080324 cites W2888249290 @default.
• W4304080324 cites W2895064504 @default.
• W4304080324 cites W2896416928 @default.
• W4304080324 cites W2914868535 @default.
• W4304080324 cites W2916798096 @default.
• W4304080324 cites W2940963663 @default.
• W4304080324 cites W2944733694 @default.
• W4304080324 cites W2961553857 @default.
• W4304080324 cites W2963091558 @default.
• W4304080324 cites W2963377215 @default.
• W4304080324 cites W2963524571 @default.
• W4304080324 cites W2964062686 @default.
• W4304080324 cites W2964154335 @default.
• W4304080324 cites W2981860940 @default.
• W4304080324 cites W3014545861 @default.
• W4304080324 cites W3035029089 @default.
• W4304080324 cites W3035648302 @default.
• W4304080324 cites W3088102655 @default.
• W4304080324 cites W3092754310 @default.
• W4304080324 cites W3092972698 @default.
• W4304080324 cites W3093411241 @default.
• W4304080324 cites W3096609285 @default.
• W4304080324 cites W3108368634 @default.
• W4304080324 cites W3119243803 @default.
• W4304080324 cites W3119771537 @default.
• W4304080324 cites W3169998028 @default.
• W4304080324 cites W3175859725 @default.
• W4304080324 cites W3202884348 @default.
• W4304080324 cites W3204485253 @default.
• W4304080324 cites W4213019189 @default.
• W4304080324 cites W4230451144 @default.
• W4304080324 cites W4312919330 @default.
• W4304080324 doi "https://doi.org/10.1145/3503161.3547825" @default.
• W4304080324 hasPublicationYear "2022" @default.
• W4304080324 type Work @default.
• W4304080324 citedByCount "3" @default.
• W4304080324 countsByYear W43040803242023 @default.
• W4304080324 crossrefType "proceedings-article" @default.
• W4304080324 hasAuthorship W4304080324A5000432967 @default.
• W4304080324 hasAuthorship W4304080324A5010665898 @default.
• W4304080324 hasAuthorship W4304080324A5011680564 @default.
• W4304080324 hasAuthorship W4304080324A5019960435 @default.
• W4304080324 hasAuthorship W4304080324A5045727713 @default.
• W4304080324 hasConcept C111919701 @default.
• W4304080324 hasConcept C118505674 @default.
• W4304080324 hasConcept C119599485 @default.
• W4304080324 hasConcept C119857082 @default.
• W4304080324 hasConcept C126838900 @default.
• W4304080324 hasConcept C127413603 @default.
• W4304080324 hasConcept C132525143 @default.
• W4304080324 hasConcept C153180895 @default.
• W4304080324 hasConcept C154945302 @default.
• W4304080324 hasConcept C165801399 @default.
• W4304080324 hasConcept C183115368 @default.
• W4304080324 hasConcept C2777212361 @default.
• W4304080324 hasConcept C2987834672 @default.
• W4304080324 hasConcept C41008148 @default.
• W4304080324 hasConcept C46686674 @default.
• W4304080324 hasConcept C66322947 @default.
• W4304080324 hasConcept C71924100 @default.
• W4304080324 hasConcept C80444323 @default.
• W4304080324 hasConceptScore W4304080324C111919701 @default.
• W4304080324 hasConceptScore W4304080324C118505674 @default.
• W4304080324 hasConceptScore W4304080324C119599485 @default.
• W4304080324 hasConceptScore W4304080324C119857082 @default.
• W4304080324 hasConceptScore W4304080324C126838900 @default.
• W4304080324 hasConceptScore W4304080324C127413603 @default.
• W4304080324 hasConceptScore W4304080324C132525143 @default.
• W4304080324 hasConceptScore W4304080324C153180895 @default.
• W4304080324 hasConceptScore W4304080324C154945302 @default.
• W4304080324 hasConceptScore W4304080324C165801399 @default.
• W4304080324 hasConceptScore W4304080324C183115368 @default.
• W4304080324 hasConceptScore W4304080324C2777212361 @default.
• W4304080324 hasConceptScore W4304080324C2987834672 @default.
• W4304080324 hasConceptScore W4304080324C41008148 @default.
• W4304080324 hasConceptScore W4304080324C46686674 @default.
• W4304080324 hasConceptScore W4304080324C66322947 @default.

• next