# Latent Embeddings for Collective Activity Recognition

arXiv: https://arxiv.org/abs/1709.06770 · HTML: https://mlsanity.com/paper/1709.06770/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2017.

## Built on by (most cited first, 1 of 1)

- [Pose is all you need: The pose only group activity recognition system (POGARS)](https://mlsanity.com/paper/2108.04186/) (2021)

## Abstract (arXiv)

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.