HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
This work addresses the problem of comprehending complex interactivities in videos for computer vision applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of understanding visual interactivities in videos by proposing a Hierarchical Interlacement Graph (HIG) approach, which achieves superior performance in scene graph generation across five tasks as demonstrated through extensive experiments.
Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, however, struggle with a diversity of appearance, situation, position, interaction, and relation in videos. This limitation hinders the ability to fully comprehend the interplay within the complex visual dynamics of subjects. In this paper, we delve into interactivities understanding within visual content by deriving scene graph representations from dense interactivities among humans and objects. To achieve this goal, we first present a new dataset containing Appearance-Situation-Position-Interaction-Relation predicates, named ASPIRe, offering an extensive collection of videos marked by a wide range of interactivities. Then, we propose a new approach named Hierarchical Interlacement Graph (HIG), which leverages a unified layer and graph within a hierarchical structure to provide deep insights into scene changes across five distinct tasks. Our approach demonstrates superior performance to other methods through extensive experiments conducted in various scenarios.