Interpreting Context of Images using Scene Graphs
This work addresses the need for better image understanding in computer vision by incorporating object relationships, though it appears incremental as it builds on existing graph-based and SVM methods.
The paper tackles the problem of understanding visual scenes by capturing relationships between objects, which traditional object detection methods miss, and presents a model that represents images as graphs to find context using visual and semantic cues with SVMs, achieving results applicable to tasks like image retrieval and captioning.
Understanding a visual scene incorporates objects, relationships, and context. Traditional methods working on an image mostly focus on object detection and fail to capture the relationship between the objects. Relationships can give rich semantic information about the objects in a scene. The context can be conducive to comprehending an image since it will help us to perceive the relation between the objects and thus, give us a deeper insight into the image. Through this idea, our project delivers a model that focuses on finding the context present in an image by representing the image as a graph, where the nodes will the objects and edges will be the relation between them. The context is found using the visual and semantic cues which are further concatenated and given to the Support Vector Machines (SVM) to detect the relation between two objects. This presents us with the context of the image which can be further used in applications such as similar image retrieval, image captioning, or story generation.