Related papers: Scene Graph Lossless Compression with Adaptive Pre…

Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly…

Accurately predicting the possible behaviors of traffic participants is an essential capability for autonomous vehicles. Since autonomous vehicles need to navigate in dynamically changing environments, they are expected to make accurate…

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has immediate benefits for various graph learning tasks. However, existing graph condensation methods rely…

Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined…

Graphs are commonly used to represent objects, such as images and text, for pattern classification. In a dynamic world, an object may continuously evolve over time, and so does the graph extracted from the underlying object. These changes…

Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the…

Motion prediction for traffic participants is essential for a safe and robust automated driving system, especially in cluttered urban environments. However, it is highly challenging due to the complex road topology as well as the uncertain…

By taking the semantic object parsing task as an exemplar application scenario, we propose the Graph Long Short-Term Memory (Graph LSTM) network, which is the generalization of LSTM from sequential data or multi-dimensional data to general…

Graph coarsening is a widely used dimensionality reduction technique for approaching large-scale graph machine learning problems. Given a large graph, graph coarsening aims to learn a smaller-tractable graph while preserving the properties…

Prediction of movements is essential for successful cooperation with intelligent systems. We propose a model that integrates organized spatial information as given through the moving body's skeletal structure. This inherent structure is…

To truly understand the visual world our models should be able not only to recognize images but also generate them. To this end, there has been exciting recent progress on generating images from natural language descriptions. These methods…

Graph-based transforms have been shown to be powerful tools in terms of image energy compaction. However, when the support increases to best capture signal dependencies, the computation of the basis functions becomes rapidly untractable.…

For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual information. To solve this, we propose a novel weakly supervised…

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph…

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured…

Scene Graph Generation (SGG) is a visual understanding task, aiming to describe a scene as a graph of entities and their relationships with each other. Existing works rely on location labels in form of bounding boxes or segmentation masks,…

Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes…

Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an…

Text-conditioned image generation has made significant progress in recent years with generative adversarial networks and more recently, diffusion models. While diffusion models conditioned on text prompts have produced impressive and…

Research techniques in the last decade have improved lossless compression ratios by significantly increasing processing time. These techniques have remained obscure because production systems require high throughput and low resource…