Temporal Attention

Temporal attention studies how models select and combine information from different moments, helping them track change, use long-range context, and focus on relevant events. Common approaches include Transformer self- and cross-attention with temporal or relative-time encodings, local-window attention, and efficient variants that combine attention with recurrent or gated aggregation. These methods are used in video action recognition and grounding, video generation, time-series forecasting, and irregular clinical records, and are evaluated on task-specific video and forecasting benchmarks. A central challenge is balancing long-range context and computational cost, while attention weights may not reliably explain which moments drove a prediction.