Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives
This work addresses the need for autonomous systems to efficiently learn and correlate multiple video understanding tasks, though it is incremental as it builds on the existing EgoPack framework.
The paper tackles the problem of holistic egocentric video understanding by extending EgoPack to handle diverse temporal granularities, enabling simultaneous reasoning across clip-level and frame-level tasks on Ego4d benchmarks.
Our comprehension of video streams depicting human activities is naturally multifaceted: in just a few moments, we can grasp what is happening, identify the relevance and interactions of objects in the scene, and forecast what will happen soon, everything all at once. To endow autonomous systems with such a holistic perception, learning how to correlate concepts, abstract knowledge across diverse tasks, and leverage tasks synergies when learning novel skills is essential. A significant step in this direction is EgoPack, a unified framework for understanding human activities across diverse tasks with minimal overhead. EgoPack promotes information sharing and collaboration among downstream tasks, essential for efficiently learning new skills. In this paper, we introduce Hier-EgoPack, which advances EgoPack by enabling reasoning also across diverse temporal granularities, which expands its applicability to a broader range of downstream tasks. To achieve this, we propose a novel hierarchical architecture for temporal reasoning equipped with a GNN layer specifically designed to tackle the challenges of multi-granularity reasoning effectively. We evaluate our approach on multiple Ego4d benchmarks involving both clip-level and frame-level reasoning, demonstrating how our hierarchical unified architecture effectively solves these diverse tasks simultaneously.