Related papers: H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Sc…
3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal…
Over the years, scene understanding has attracted a growing interest in computer vision, providing the semantic and physical scene information necessary for robots to complete some particular tasks autonomously. In 3D scenes, rich spatial…
Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations…
Discovering human cognitive and emotional states using multi-modal physiological signals draws attention across various research applications. Physiological responses of the human body are influenced by human cognition and commonly used to…
This paper continues a geometric study of Harvey's Complex of Curves, whose ultimate goal is to apply the theory of hyperbolic spaces and groups to algorithmic questions for the Mapping Class Group and geometric properties of Kleinian…
Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds,…
Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, single-view…
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…
Achieving visual semantic understanding requires a unified framework that simultaneously handles object detection, category prediction, and attribute recognition. However, current advanced approaches rely on global similarity and struggle…
Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding and object-level relocalization when a robot revisits a…
The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing,…
Graph representation learning in Euclidean space, despite its widespread adoption and proven utility in many domains, often struggles to effectively capture the inherent hierarchical and complex relational structures prevalent in real-world…
Temporal link prediction, aiming to predict future edges between paired nodes in a dynamic graph, is of vital importance in diverse applications. However, existing methods are mainly built upon uniform Euclidean space, which has been found…
Spatial Transcriptomics (ST) merges the benefits of pathology images and gene expression, linking molecular profiles with tissue structure to analyze spot-level function comprehensively. Predicting gene expression from histology images is a…
Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…
Generalized few-shot 3D point cloud segmentation aims to adapt to novel classes from only a few annotations while maintaining strong performance on base classes, but this remains challenging due to the inherent stability-plasticity…
In this paper we consider a large family of graphs of hierarchically hyperbolic groups (HHG) and show that their fundamental groups admit HHG structures. To do that, we will investigate the notion of hierarchical quasi convexity and show…
Visual grouping is a key mechanism in human scene perception. There, it belongs to the subconscious, early processing and is key prerequisite for other high level tasks such as recognition. In this paper, we introduce an efficient, realtime…
We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human…
Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations.…