Attentive pooling for Group Activity Recognition
This work addresses the problem of accurately recognizing group activities in computer vision, which is incremental as it improves upon existing hierarchical models by incorporating attention mechanisms.
The paper tackled the problem of group activity recognition by proposing attentive pooling to address the limitation of max/average pooling in hierarchical frameworks, resulting in superior performance compared to baselines and competitive results with state-of-the-art methods on benchmark datasets.
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.