EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding

TL;DR

EgoGraph introduces a dynamic knowledge-graph framework for egocentric videos, enabling long-term temporal reasoning and improved understanding over extended sequences, surpassing traditional clip-based methods.

Contribution

The paper presents a novel, training-free knowledge-graph construction method that captures long-term dependencies and attributes in egocentric videos for enhanced semantic reasoning.

Findings

Achieves state-of-the-art results on long-term video question answering benchmarks.

Effectively models long-term dependencies across days in egocentric videos.

Enables complex temporal reasoning through a new relational modeling strategy.

Abstract

Ultra-long egocentric videos spanning multiple days present significant challenges for video understanding. Existing approaches still rely on fragmented local processing and limited temporal modeling, restricting their ability to reason over such extended sequences. To address these limitations, we introduce EgoGraph, a training-free and dynamic knowledge-graph construction framework that explicitly encodes long-term, cross-entity dependencies in egocentric video streams. EgoGraph employs a novel egocentric schema that unifies the extraction and abstraction of core entities, such as people, objects, locations, and events, and structurally reasons about their attributes and interactions, yielding a significantly richer and more coherent semantic representation than traditional clip-based video models. Crucially, we develop a temporal relational modeling strategy that captures temporal dependencies across entities and accumulates stable long-term memory over multiple days, enabling complex temporal reasoning. Extensive experiments on the EgoLifeQA and EgoR1-bench benchmarks demonstrate that EgoGraph achieves state-of-the-art performance on long-term video question answering, validating its effectiveness as a new paradigm for ultra-long egocentric video understanding.