A group activity recognition framework uses two reinforcement-learning agents to distill informative frames and gate relation edges in a semantic graph, outperforming prior methods on Volleyball and Collective Activity datasets.
Bagautdinov, Alexandre Alahi, Franc ¸ois Fleuret, Pascal Fua, and Silvio Savarese
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Progressive Relation Learning for Group Activity Recognition
A group activity recognition framework uses two reinforcement-learning agents to distill informative frames and gate relation edges in a semantic graph, outperforming prior methods on Volleyball and Collective Activity datasets.