Related papers: Scene Graph Lossless Compression with Adaptive Pre…
Visual Commonsense Reasoning, which is regarded as one challenging task to pursue advanced visual scene comprehension, has been used to diagnose the reasoning ability of AI systems. However, reliable reasoning requires a good grasp of the…
We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context…
This paper addresses the problem of traffic prediction in distributed backend systems and proposes a graph neural network based modeling approach to overcome the limitations of traditional models in capturing complex dependencies and…
Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms (e.g., graph Fourier or…
In this work, we seek new insights into the underlying challenges of the Scene Graph Generation (SGG) task. Quantitative and qualitative analysis of the Visual Genome dataset implies -- 1) Ambiguity: even if inter-object relationship…
Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared…
A proper scene representation is central to the pursuit of spatial intelligence where agents can robustly reconstruct and efficiently understand 3D scenes. A scene representation is either metric, such as landmark maps in 3D reconstruction,…
Research in scene graph generation has quickly gained traction in the past few years because of its potential to help in downstream tasks like visual question answering, image captioning, etc. Many interesting approaches have been proposed…
Scene graphs have become an important form of structured knowledge for tasks such as for image generation, visual relation detection, visual question answering, and image retrieval. While visualizing and interpreting word embeddings is well…
2D scene graphs provide a structural and explainable framework for scene understanding. However, current work still struggles with the lack of accurate scene graph data. To overcome this data bottleneck, we present CoPa-SG, a synthetic…
Scene graph generation aims to provide a semantic and structural description of an image, denoting the objects (with nodes) and their relationships (with edges). The best performing works to date are based on exploiting the context…
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting…
Crowd counting, i.e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications. A key component for the crowd counting systems is the construction of counting…
This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge. Specifically, we begin by proposing a hierarchical relation head that exploits an informative…
Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. However, these methods have two critical issues: first, deep graph convolutions…
Embodied AI agents that search for objects in large environments such as households often need to make efficient decisions by predicting object locations based on partial information. We pose this as a new type of link prediction problem:…
A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an…
To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself. Inspired by human…
Representing a dynamic scene using a structured spatial-temporal scene graph is a novel and particularly challenging task. To tackle this task, it is crucial to learn the temporal interactions between objects in addition to their spatial…
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors…