Latent Embeddings for Collective Activity Recognition
This work addresses the challenge of recognizing group activities in collective scenes, which is important for applications like surveillance and social behavior analysis, and is incremental by improving upon existing methods with new embeddings and attention mechanisms.
The paper tackled the problem of collective activity recognition by embedding latent variables into feature space within a deep learning framework to model complex structural dependencies among individuals, achieving clearly better performance compared to state-of-the-art methods on three datasets.
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials in conventional graphical model which can only define a limited range of relations. Thus, the complex structural de- pendencies among individuals involved in a collective sce- nario cannot be fully modeled. In this paper, we overcome these limitations by embedding latent variables into feature space and learning the feature mapping functions in a deep learning framework. The embeddings of latent variables build a global relation containing person-group interac- tions and richer contextual information by jointly modeling broader range of individuals. Besides, we assemble atten- tion mechanism during embedding for achieving more com- pact representations. We evaluate our method on three col- lective activity datasets, where we contribute a much larger dataset in this work. The proposed model has achieved clearly better performance as compared to the state-of-the- art methods in our experiments.