Related papers: Learning Inner-Group Relations on Point Clouds

Robust principal component analysis (RPCA) decomposes an observation matrix into low-rank background and sparse object components. This capability has enabled its application in tasks ranging from image restoration to segmentation. However,…

A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training. Tasks such as similarity matching and input reconstruction…

We create a family of powerful video models which are able to: (i) learn interactions between semantic object information and raw appearance and motion features, and (ii) deploy attention in order to better learn the importance of features…

Graph Neural Networks (GNNs) have excelled in learning from graph-structured data, especially in understanding the relationships within a single graph, i.e., intra-graph relationships. Despite their successes, GNNs are limited by neglecting…

With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community. Existing methods usually formulate the mapping function as the similarity…

Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation…

In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and…

Community structure is largely regarded as an intrinsic property of complex real-world networks. However, recent studies reveal that networks comprise even more sophisticated modules than classical cohesive communities. More precisely,…

We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers. Such aggregation is critical to facilitate…

Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object…

Raw point clouds data inevitably contains outliers or noise through acquisition from 3D sensors or reconstruction algorithms. In this paper, we present a novel end-to-end network for robust point clouds processing, named PointASNL, which…

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point…

Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints. Recent methods based on deep learning utilize a global average pooling…

We propose a method for demonstrating sub community structure in scientific networks of relatively small size from analyzing databases of publications. Research relationships between the network members can be visualized as a graph with…

Clustering points in a vector space or nodes in a graph is a ubiquitous primitive in statistical data analysis, and it is commonly used for exploratory data analysis. In practice, it is often of interest to "refine" or "improve" a given…

Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

Recommendation to groups of users is a challenging subfield of recommendation systems. Its key concept is how and where to make the aggregation of each set of user information into an individual entity, such as a ranked recommendation list,…

Graph clustering is a fundamental problem that has been extensively studied both in theory and practice. The problem has been defined in several ways in literature and most of them have been proven to be NP-Hard. Due to their high practical…

Cross-view geo-localisation (CVGL) aims to estimate the geographic location of a query image by matching it with images from a large-scale database. However, the significant view-point discrepancies present considerable challenges for…