Breaking The Synopsis Trade-off: Preserving Event Cohesion Via Community-aware Graph Packing

Video synopsis condenses long surveillance recordings into concise, informative summaries. Existing methods often sacrifice narrative continuity, dispersing related events across the timeline to achieve higher compression. In this work, we reframe the task by modeling video content as a heterogeneous interaction graph. A Graph Neural Network (GNN) computes context-aware refinements of heuristic importance scores for objects, capturing the nuanced relationships that define complex scenes. At the core of our framework lies a community-aware packing algorithm, which schedules event-based communities rather than individual objects, thereby preserving temporal and semantic integrity. Extensive experiments show that our approach surpasses the conventional compression-quality trade-off, achieving ۵۸% higher compression rates than the existing benchmark method while reducing visual clutter. We introduce the Community Cohesion Ratio (CCR), a task-specific evaluation metric designed to quantify the preservation of relative temporal relationships among objects belonging to the same event community. Using this complementary metric, our approach achieves an ۸۸% lower CCR value than the standard packing method, indicating improved preservation of temporal community structure.

کلیدواژه ها:

Video Synopsis ، Event Cohesion ، Graph Packing ، community detection ، graph neural networks