GROWL: Group Detection With Link Prediction
- URL: http://arxiv.org/abs/2111.04397v1
- Date: Mon, 8 Nov 2021 11:52:48 GMT
- Title: GROWL: Group Detection With Link Prediction
- Authors: Viktor Schmuck, Oya Celiktutan
- Abstract summary: We propose a holistic approach to group detection based on Graph Neural Networks (GNNs)
Our proposed method, GROup detection With Link prediction, demonstrates the effectiveness of a GNN based approach.
Our results show that a GNN based approach can significantly improve accuracy across different camera views.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Interaction group detection has been previously addressed with bottom-up
approaches which relied on the position and orientation information of
individuals. These approaches were primarily based on pairwise affinity
matrices and were limited to static, third-person views. This problem can
greatly benefit from a holistic approach based on Graph Neural Networks (GNNs)
beyond pairwise relationships, due to the inherent spatial configuration that
exists between individuals who form interaction groups. Our proposed method,
GROup detection With Link prediction (GROWL), demonstrates the effectiveness of
a GNN based approach. GROWL predicts the link between two individuals by
generating a feature embedding based on their neighbourhood in the graph and
determines whether they are connected with a shallow binary classification
method such as Multi-layer Perceptrons (MLPs). We test our method against other
state-of-the-art group detection approaches on both a third-person view dataset
and a robocentric (i.e., egocentric) dataset. In addition, we propose a
multimodal approach based on RGB and depth data to calculate a representation
GROWL can utilise as input. Our results show that a GNN based approach can
significantly improve accuracy across different camera views, i.e.,
third-person and egocentric views.
Related papers
- Improving Link Prediction in Social Networks Using Local and Global
Features: A Clustering-based Approach [0.0]
We propose an approach based on the combination of first and second group methods to tackle the link prediction problem.
Our two-phase developed method firstly determines new features related to the position and dynamic behavior of nodes.
Then, a subspace clustering algorithm is applied to group social objects based on the computed similarity measures.
arXiv Detail & Related papers (2023-05-17T14:45:02Z) - Rethinking the positive role of cluster structure in complex networks
for link prediction tasks [1.4695979686066065]
Clustering is a problem in network analysis that finds closely connected groups of nodes.
Link prediction is to predict whether two nodes in a network are likely to have a link.
We construct a simple but efficient clustering-driven link prediction framework.
arXiv Detail & Related papers (2022-11-04T12:02:40Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - RU-Net: Regularized Unrolling Network for Scene Graph Generation [92.95032610978511]
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects.
Existing SGG methods usually suffer from several issues, including 1) ambiguous object representations, and 2) low diversity in relationship predictions.
We propose a regularized unrolling network (RU-Net) to address both problems.
arXiv Detail & Related papers (2022-05-03T04:21:15Z) - A Variational Edge Partition Model for Supervised Graph Representation
Learning [51.30365677476971]
This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities.
We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs.
A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
arXiv Detail & Related papers (2022-02-07T14:37:50Z) - Measuring inter-cluster similarities with Alpha Shape TRIangulation in
loCal Subspaces (ASTRICS) facilitates visualization and clustering of
high-dimensional data [0.0]
Clustering and visualizing high-dimensional (HD) data are important tasks in a variety of fields.
Some of the most effective algorithms for clustering HD data are based on representing the data by nodes in a graph.
I propose a new method called ASTRICS to measure similarity between clusters of HD data points.
arXiv Detail & Related papers (2021-07-15T20:51:06Z) - Learning Spatial Context with Graph Neural Network for Multi-Person Pose
Grouping [71.59494156155309]
Bottom-up approaches for image-based multi-person pose estimation consist of two stages: keypoint detection and grouping.
In this work, we formulate the grouping task as a graph partitioning problem, where we learn the affinity matrix with a Graph Neural Network (GNN)
The learned geometry-based affinity is further fused with appearance-based affinity to achieve robust keypoint association.
arXiv Detail & Related papers (2021-04-06T09:21:14Z) - DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
We tackle the challenging problem of human-object interaction (HOI) detection.
Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features.
In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
arXiv Detail & Related papers (2020-08-26T17:59:40Z) - Learning to Cluster Faces via Confidence and Connectivity Estimation [136.5291151775236]
We propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs.
Our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.
arXiv Detail & Related papers (2020-04-01T13:39:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.