Oct 3, 2023 · The article proposes the spatio-temporal object knowledge graph (STOKG), consisting of the object concept layer, spatio-temporal object layer, and dynamic ...

Spatio‐temporal knowledge is essential in understanding the dynamic aspects of complex scenes. However, existing knowledge graphs have limitations, ...

This paper puts forward a fresh approach: a new self-supervised dynamic spatio-temporal graph convolutional network (SDSC) for traffic flow forecasting.

We propose a novel and effective knowledge graph embedding model called Version Embedding (VerE), which embeds continuous time into vector space.

Mar 18, 2024 · To evaluate the effectiveness of our proposed HiKER-SGG, we conduct comprehensive experiments on both the original clean Visual Genome (VG) ...

It is a graph-based representation de- scribing interactions between objects in the image. Nodes in the scene graph indicate the objects while edges denote the.

By expanding a single node into multiple sub-nodes representing different statuses of a geographic entity, this model can link the spatiotemporal features, ...

A scene graph is a topological structure representing a scene described in text, image, video, or etc. In this graph, the nodes correspond to object bounding ...

This paper explores automatic summarization techniques that characterize and enable identification of an entity and create summaries that are human friendly.

Mar 3, 2022 · Such a (2.5+1)D graph is then segregated into a static sub-graph and a dynamic sub-graph, corresponding to whether the objects within them ...