Scene Graph Generation from Objects, Phrases and Region Captions
This addresses scene understanding for computer vision applications by integrating multiple semantic levels, though it is incremental as it builds on existing tasks and methods.
The paper tackles the joint learning of object detection, scene graph generation, and region captioning by proposing a Multi-level Scene Description Network (MSDN) that aligns these tasks through a dynamic graph and feature refining structure. The result shows mutual improvements across tasks, with scene graph generation outperforming the state-of-the-art by over 3%.
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision tasks jointly in an end-to-end manner. Objects, phrases, and caption regions are first aligned with a dynamic graph based on their spatial and semantic connections. Then a feature refining structure is used to pass messages across the three levels of semantic tasks through the graph. We benchmark the learned model on three tasks, and show the joint learning across three tasks with our proposed method can bring mutual improvements over previous models. Particularly, on the scene graph generation task, our proposed method outperforms the state-of-art method with more than 3% margin.