A Hierarchical Deep Temporal Model for Group Activity Recognition
This work addresses activity recognition in groups, which is important for video analysis applications, but it is incremental as it builds on existing LSTM-based approaches.
The paper tackles group activity recognition by proposing a hierarchical deep temporal model using LSTMs to capture individual and group dynamics, and it reports improved performance on two datasets compared to baseline methods.
In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity. We build a deep model to capture these dynamics based on LSTM (long-short term memory) models. To make use of these ob- servations, we present a 2-stage deep temporal model for the group activity recognition problem. In our model, a LSTM model is designed to represent action dynamics of in- dividual people in a sequence and another LSTM model is designed to aggregate human-level information for whole activity understanding. We evaluate our model over two datasets: the collective activity dataset and a new volley- ball dataset. Experimental results demonstrate that our proposed model improves group activity recognition perfor- mance with compared to baseline methods.