THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage

TL;DR

THYME introduces a hierarchical cyclic model for video scene graphs that captures multi-scale spatial and temporal dependencies, improving scene understanding in aerial and ground videos.

Contribution

It proposes the THYME framework combining hierarchical feature aggregation with cyclic temporal refinement for better scene graph generation.

Findings

Outperforms existing methods on ASPIRe and AeroEye-v1.0 datasets.

Effectively models multi-scale spatial context and temporal consistency.

Provides a new aerial video dataset with comprehensive interactivity annotations.

Abstract

The rapid proliferation of video in applications such as autonomous driving, surveillance, and sports analytics necessitates robust methods for dynamic scene understanding. Despite advances in static scene graph generation and early attempts at video scene graph generation, previous methods often suffer from fragmented representations, failing to capture fine-grained spatial details and long-range temporal dependencies simultaneously. To address these limitations, we introduce the Temporal Hierarchical Cyclic Scene Graph (THYME) approach, which synergistically integrates hierarchical feature aggregation with cyclic temporal refinement to address these limitations. In particular, THYME effectively models multi-scale spatial context and enforces temporal consistency across frames, yielding more accurate and coherent scene graphs. In addition, we present AeroEye-v1.0, a novel aerial video dataset enriched with five types of interactivity that overcome the constraints of existing datasets and provide a comprehensive benchmark for dynamic scene graph generation. Empirically, extensive experiments on ASPIRe and AeroEye-v1.0 demonstrate that the proposed THYME approach outperforms state-of-the-art methods, offering improved scene understanding in ground-view and aerial scenarios.