# Attentive pooling for Group Activity Recognition

arXiv: https://arxiv.org/abs/2208.14847 · HTML: https://mlsanity.com/paper/2208.14847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 31 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Hierarchical Deep Temporal Models for Group Activity Recognition](https://mlsanity.com/paper/1607.02643/) (2016)
- [Long-term Temporal Convolutions for Action Recognition](https://mlsanity.com/paper/1604.04494/) (2016)
- [VideoLSTM Convolves, Attends and Flows for Action Recognition](https://mlsanity.com/paper/1607.01794/) (2016)
- [Going Deeper into Action Recognition: A Survey](https://mlsanity.com/paper/1605.04988/) (2016)
- [Action Recognition using Visual Attention](https://mlsanity.com/paper/1511.04119/) (2015)
- [Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition](https://mlsanity.com/paper/1611.09078/) (2016)
- [Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification](https://mlsanity.com/paper/1711.09550/) (2017)
- [CERN: Confidence-Energy Recurrent Network for Group Activity Recognition](https://mlsanity.com/paper/1704.03058/) (2017)
- [Structural Recurrent Neural Network (SRNN) for Group Activity Analysis](https://mlsanity.com/paper/1802.02091/) (2018)

## Abstract (arXiv)

In group activity recognition, hierarchical framework is widely adopted to represent the relationships between individuals and their corresponding group, and has achieved promising performance. However, the existing methods simply employed max/average pooling in this framework, which ignored the distinct contributions of different individuals to the group activity recognition. In this paper, we propose a new contextual pooling scheme, named attentive pooling, which enables the weighted information transition from individual actions to group activity. By utilizing the attention mechanism, the attentive pooling is intrinsically interpretable and able to embed member context into the existing hierarchical model. In order to verify the effectiveness of the proposed scheme, two specific attentive pooling methods, i.e., global attentive pooling (GAP) and hierarchical attentive pooling (HAP) are designed. GAP rewards the individuals that are significant to group activity, while HAP further considers the hierarchical division by introducing subgroup structure. The experimental results on the benchmark dataset demonstrate that our proposal is significantly superior beyond the baseline and is comparable to the state-of-the-art methods.